Paper Citation Record · LEDGER

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model

As of 23 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 11 inbound Pith citation observations for arXiv:2505.15670.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.15670 v4

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:15:42.078895Z

measured 56 of 56 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 11 of 11 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:15:39.489566Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-08T00:04:22.333058Z

Reference resolution

45 of 45 outbound references displayed

verified exact0
verified fuzzy13
unresolved32
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 608b3f37-327f-4f88-835f-119c63fa7a90 · outbound

This paper cites Speech, as a natural interface for human-computer interaction, is a key part of this trend.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Speech, as a natural interface for human-computer interaction, is a key part of this trend

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:42.444460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0b6a9737-094d-4609-88eb-c1b000bbc7ba · outbound

This paper cites SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:39.489566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1b9f11c-8d29-43ee-ba4c-b556f2eee5dd · outbound

This paper cites As shown in Fig.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model As shown in Fig

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:42.433740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 79f804ef-dbc8-48b1-a57b-ac24569865ea · outbound

This paper cites an unresolved cited work.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:15:42.425804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 99396500-d067-459a-9845-140e8de2e21e · outbound

This paper cites Training Details We implement the model with PyTorch using the NeMo Toolkit [32], and the model is trained on 32 A100 (80G) GPUs with a batch duration of 1000 sec per GPU.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Training Details We implement the model with PyTorch using the NeMo Toolkit [32], and the model is trained on 32 A100 (80G) GPUs with a batch duration of 1000 sec per GPU

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:42.417215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4d4a84b0-866b-4c43-8599-934ee54ae2f6 · outbound

This paper cites Conversation and Speech Generation Quality We first evaluate the turn-taking and speech generation quality of our model in Table 2.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Conversation and Speech Generation Quality We first evaluate the turn-taking and speech generation quality of our model in Table 2

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:42.398893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6833835f-f91d-4e7d-9e7d-4ba2e93057f8 · outbound

This paper cites Our data-efficient approach maintains end-to-end modeling of conversation reasoning and behaviors.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Our data-efficient approach maintains end-to-end modeling of conversation reasoning and behaviors

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:42.389893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e61263e1-31a4-4cb4-b4f6-7069e922801f · outbound

This paper cites Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:40.710921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f045280f-02f7-4c23-a8ed-63968d3b255a · outbound

This paper cites Language Models are Few-Shot Learners.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Language Models are Few-Shot Learners

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:40.323064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e1a562f-c683-4837-920a-c238882f3c59 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:40.358344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87bfc2ab-8c94-494f-91e6-56f030755e9d · outbound

This paper cites GPT-4 Technical Report.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model GPT-4 Technical Report

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:40.458268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3efeab3a-be21-477e-bf0f-88c8d0026d4f · outbound

This paper cites The Llama 3 Herd of Models.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model The Llama 3 Herd of Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:40.495309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa3a7013-6dce-4a0d-8559-83742fb163db · outbound

This paper cites Prompting large lan- guage models with speech recognition abilities,.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Prompting large lan- guage models with speech recognition abilities,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:42.381098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a37d437a-5e04-4921-b1a6-cdd4a1f11072 · outbound

This paper cites Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:40.576987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10fc18f8-d107-4c65-b84b-79018482b431 · outbound

This paper cites Salm: Speech- augmented language model with in-context learning for speech recognition and translation,.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Salm: Speech- augmented language model with in-context learning for speech recognition and translation,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:42.373175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f8de665c-47f6-46ec-bace-b58b78ad2f12 · outbound

This paper cites MinMo: A Multimodal Large Language Model for Seamless Voice Interaction.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model MinMo: A Multimodal Large Language Model for Seamless Voice Interaction

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.249905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5de911f-2e4c-478b-ba2d-aa3d87b706db · outbound

This paper cites Chain-of-Thought Prompting for Speech Translation.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Chain-of-Thought Prompting for Speech Translation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:40.786047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fe7e413-a417-44d9-9241-a2d73bb7e9e8 · outbound

This paper cites Audiogpt: Understanding and generating speech, music, sound, and talking head,.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Audiogpt: Understanding and generating speech, music, sound, and talking head,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:40.841899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01a6c0b4-dc2f-43c3-9ed7-5e368dccc600 · outbound

This paper cites SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:40.897400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38142bf8-5591-46c9-98fd-aaf614f8ae83 · outbound

This paper cites Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:40.984202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39200706-e687-4c09-9335-2c5b907af55e · outbound

This paper cites GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.059351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ace2e86-a54f-4556-bce4-86c0b5df85a0 · outbound

This paper cites Moshi: a speech-text foundation model for real-time dialogue.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Moshi: a speech-text foundation model for real-time dialogue

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.113033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db328e41-823a-4af7-af87-23a964b4f75d · outbound

This paper cites SALMONN-omni: A Codec-free LLM for Full-duplex Speech Understanding and Generation.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model SALMONN-omni: A Codec-free LLM for Full-duplex Speech Understanding and Generation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.192273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d69e0e4-cd4a-4954-91cd-920b36bfd365 · outbound

This paper cites Language Model Can Listen While Speaking.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Language Model Can Listen While Speaking

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.553345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85dcecb1-992d-4578-8b26-c89e185417b4 · outbound

This paper cites OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.290160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33b497fc-fbcc-4410-a8e5-9be4634c3e0a · outbound

This paper cites Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.303521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4063eb1b-f800-41e0-9f90-47c4c9ea75bf · outbound

This paper cites Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.330420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d5f9da1-3b89-427f-b157-5f391fb774f5 · outbound

This paper cites Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.384675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0eb5ef39-3078-4bb0-824d-ab55b1f8e210 · outbound

This paper cites STT En FastConformer Hybrid Transducer- CTC Large Streaming 80ms,.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model STT En FastConformer Hybrid Transducer- CTC Large Streaming 80ms,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:42.360642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d0a9ae32-ff49-4c84-ad16-77cff57fa3db · outbound

This paper cites Tinyllama: An open- source small language model,.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Tinyllama: An open- source small language model,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:42.352226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f359ab48-b432-4563-8c82-6e8c4bdc8a3c · outbound

This paper cites Nanocodec: Towards high-quality ultra fast speech llm inference,.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Nanocodec: Towards high-quality ultra fast speech llm inference,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:42.343551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 48467ded-daf0-47ac-816a-8968de5ac28d · outbound

This paper cites NeMo: a toolkit for building AI applications using Neural Modules.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model NeMo: a toolkit for building AI applications using Neural Modules

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.858736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7766c92-50da-4dff-adca-bdeaffa7b8f3 · outbound

This paper cites an unresolved cited work.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:15:42.407141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c2f78b49-9ca8-4db3-baac-27a63f3685a1 · outbound

This paper cites Finite Scalar Quantization: VQ-VAE Made Simple.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Finite Scalar Quantization: VQ-VAE Made Simple

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.585656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8be44fe8-916e-4a1c-96e3-392b51f16bab · outbound

This paper cites Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.620262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d149fbc4-f14f-408b-bf49-7fc3feaa4627 · outbound

This paper cites MS MARCO: A Human Generated MAchine Reading COmprehension Dataset.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model MS MARCO: A Human Generated MAchine Reading COmprehension Dataset

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.665957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afeb7db7-fe2c-4f92-81b3-1c2bb52de6da · outbound

This paper cites Stanford alpaca: An instruction- following llama model,.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Stanford alpaca: An instruction- following llama model,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:42.335636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0303236c-1072-4fcf-97c2-6f6758f0a3d4 · outbound

This paper cites Instruction Data Generation and Unsupervised Adaptation for Speech Language Models.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Instruction Data Generation and Unsupervised Adaptation for Speech Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.737032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b269f047-b8b3-4a58-8d0d-590bb98753ca · outbound

This paper cites Everyday conversations for llms,.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Everyday conversations for llms,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:42.326808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 81779223-e5d3-45f2-ad43-c20072f0cc4e · outbound

This paper cites Enhancing Chat Language Models by Scaling High-quality Instructional Conversations.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Enhancing Chat Language Models by Scaling High-quality Instructional Conversations

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.815909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ff242c2-36ba-48cb-9490-3526bb759a91 · outbound

This paper cites UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.893922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09695c8b-9ad6-4b6b-acb4-df096bd30edc · outbound

This paper cites Torchaudio-squim: Reference-less speech quality and intelligibility measures in torchaudio,.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Torchaudio-squim: Reference-less speech quality and intelligibility measures in torchaudio,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:42.317772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3a9b70f2-c4a3-49f7-ae7a-391d68da4bcb · outbound

This paper cites Scaling speech technology to 1,000+ languages,.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Scaling speech technology to 1,000+ languages,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:41.996729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93cb78a0-cf8f-4920-a0ab-345b6f8ee6d4 · outbound

This paper cites Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone,.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:42.069009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3709e300-8916-4d0d-b697-2a6974bb8e19 · outbound

This paper cites ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddings.

SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddings

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:42.078895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 0b6a9737-094d-4609-88eb-c1b000bbc7ba · inbound