REVIEW 2 cited by
VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech
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
read the original abstract
Recent TTS models with decoder-only Transformer architecture, such as SPEAR-TTS and VALL-E, achieve impressive naturalness and demonstrate the ability for zero-shot adaptation given a speech prompt. However, such decoder-only TTS models lack monotonic alignment constraints, sometimes leading to hallucination issues such as mispronunciation, word skipping and repeating. To address this limitation, we propose VALL-T, a generative Transducer model that introduces shifting relative position embeddings for input phoneme sequence, explicitly indicating the monotonic generation process while maintaining the architecture of decoder-only Transformer. Consequently, VALL-T retains the capability of prompt-based zero-shot adaptation and demonstrates better robustness against hallucinations with a relative reduction of 28.3% in the word error rate.
Forward citations
Cited by 2 Pith papers
-
SpeakStream: Streaming Text-to-Speech with Interleaved Data
A decoder-only TTS trained on force-aligned interleaved text-speech chunks generates audio after a few words, achieving ~30ms TTS latency and WER comparable to non-streaming.
-
Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding
Masked self-distillation training plus semi-autoregressive decoding improves RNN-T keyword spotting recall at low false alarm rates, especially in noisy conditions.
Discussion (0). Continue with ORCID to comment.