Pith. sign in

REVIEW 3 cited by

SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.02328 v3 pith:U7L3BSXX submitted 2024-06-04 cs.SD eess.AS

classification cs.SDeess.AS
keywords latentspeechdiffusionscalarspacesq-codecmodelsimplespeech
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this study, we propose a simple and efficient Non-Autoregressive (NAR) text-to-speech (TTS) system based on diffusion, named SimpleSpeech. Its simpleness shows in three aspects: (1) It can be trained on the speech-only dataset, without any alignment information; (2) It directly takes plain text as input and generates speech through an NAR way; (3) It tries to model speech in a finite and compact latent space, which alleviates the modeling difficulty of diffusion. More specifically, we propose a novel speech codec model (SQ-Codec) with scalar quantization, SQ-Codec effectively maps the complex speech signal into a finite and compact latent space, named scalar latent space. Benefits from SQ-Codec, we apply a novel transformer diffusion model in the scalar latent space of SQ-Codec. We train SimpleSpeech on 4k hours of a speech-only dataset, it shows natural prosody and voice cloning ability. Compared with previous large-scale TTS models, it presents significant speech quality and generation speed improvement. Demos are released.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking

    cs.LG 2026-02 conditional novelty 6.0 of 10

    UPipe chunks attention by head so QKV and all-to-all buffers scale with a small tunable chunk size rather than head count, enabling 5M-token Llama3-8B training on one 8×H100 node with throughput close to Ulysses.

  2. Adaptive Duration Model for Text Speech Alignment

    cs.SD 2025-07 conditional novelty 5.0 of 10

    DurFormer, an adaptive duration prediction model with speed, scene, and semantic conditioning, improves phoneme-level duration accuracy and lowers word error rate in Mandarin text-to-speech.

  3. IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech

    cs.CL 2025-06 conditional novelty 5.0 of 10

    IndexTTS2 achieves precise token-count-based duration control and emotion/speaker disentanglement in an autoregressive zero-shot TTS, reporting SOTA WER, speaker similarity, and emotional fidelity.

Pith tools