Pith. sign in

REVIEW 6 cited by

AdaSpeech: Adaptive Text to Speech for Custom Voice

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 2103.00993 v1 pith:HVYHFAQK submitted 2021-03-01 eess.AS cs.AIcs.CLcs.SD

classification eess.AScs.AIcs.CLcs.SD
keywords speechvoiceadaptationadaspeechacousticcustomspeakerconditions
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Custom voice, a specific text to speech (TTS) service in commercial speech platforms, aims to adapt a source TTS model to synthesize personal voice for a target speaker using few speech data. Custom voice presents two unique challenges for TTS adaptation: 1) to support diverse customers, the adaptation model needs to handle diverse acoustic conditions that could be very different from source speech data, and 2) to support a large number of customers, the adaptation parameters need to be small enough for each target speaker to reduce memory usage while maintaining high voice quality. In this work, we propose AdaSpeech, an adaptive TTS system for high-quality and efficient customization of new voices. We design several techniques in AdaSpeech to address the two challenges in custom voice: 1) To handle different acoustic conditions, we use two acoustic encoders to extract an utterance-level vector and a sequence of phoneme-level vectors from the target speech during training; in inference, we extract the utterance-level vector from a reference speech and use an acoustic predictor to predict the phoneme-level vectors. 2) To better trade off the adaptation parameters and voice quality, we introduce conditional layer normalization in the mel-spectrogram decoder of AdaSpeech, and fine-tune this part in addition to speaker embedding for adaptation. We pre-train the source TTS model on LibriTTS datasets and fine-tune it on VCTK and LJSpeech datasets (with different acoustic conditions from LibriTTS) with few adaptation data, e.g., 20 sentences, about 1 minute speech. Experiment results show that AdaSpeech achieves much better adaptation quality than baseline methods, with only about 5K specific parameters for each speaker, which demonstrates its effectiveness for custom voice. Audio samples are available at https://speechresearch.github.io/adaspeech/.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Huracan: A skillful end-to-end data-driven system for ensemble data assimilation and weather prediction

    physics.ao-ph 2025-08 conditional novelty 7.0 of 10

    A fully observation-driven ensemble weather forecasting system, Huracan, reports CRPS skill comparable to ECMWF ENS on 75.4% of variable and lead-time combinations.

  2. XEmoRAG: Cross-Lingual Emotion Transfer with Controllable Intensity Using Retrieval-Augmented Generation

    eess.AS 2025-08 conditional novelty 6.0 of 10

    XEmoRAG synthesizes Thai speech with emotions cloned from Chinese reference audio by retrieving matching Thai prompts and aligning prosody with flow matching, outperforming baseline TTS in emotion similarity and intel...

  3. Next Tokens Denoising for Speech Synthesis

    cs.SD 2025-07 conditional novelty 6.0 of 10

    Dragon-FM generates speech autoregressively over two-second chunks while using flow matching inside each chunk, achieving fast synthesis at 12.5 discrete audio tokens per second.

  4. GSA-TTS : Toward Zero-Shot Speech Synthesis based on Gradual Style Adaptor

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A zero-shot TTS method that splits reference audio into ASR word segments, encodes local styles, and merges them via self-attention improves intelligibility and speaker similarity on unseen voices.

  5. CRPS-LAM: Probabilistic Regional Weather Forecasting with Continuous Ranked Probability Score

    cs.LG 2025-10 conditional novelty 5.0 of 10

    CRPS-LAM produces 57-hour probabilistic limited-area forecasts on MEPS at diffusion-comparable accuracy with single-forward-pass sampling, roughly 39x faster than Diffusion-LAM.

  6. DS-TTS: Zero-Shot Speaker Style Adaptation from Voice Clips via Dynamic Dual-Style Feature Modulation

    cs.SD 2025-06 reject novelty 5.0 of 10

    DS-TTS adds a second MFCC-based style encoder and a length-adaptive variance adapter to a StyleSpeech-style TTS model, reporting higher speaker similarity but not lower WER than two strong baselines.

Pith tools