VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers
This paper introduces VALL-E 2, the latest advancement in neural codec language models that marks a milestone in zero-shot text-to-speech synthesis (TTS), achieving human parity for the first time. Based on its predecessor, VALL-E, the new iteration introduces two significant enhancements: Repetition Aware Sampling refines the original nucleus sampling process by accounting for token repetition in the decoding history. It not only stabilizes the decoding but also circumvents the infinite loop issue. Grouped Code Modeling organizes codec codes into groups to effectively shorten the sequence length, which not only boosts inference speed but also addresses the challenges of long sequence modeling. Our experiments on the LibriSpeech and VCTK datasets show that VALL-E 2 surpasses previous systems in speech robustness, naturalness, and speaker similarity. It is the first of its kind to reach human parity on these benchmarks. Moreover, VALL-E 2 consistently synthesizes high-quality speech, even for sentences that are traditionally challenging due to their complexity or repetitive phrases. The advantages of this work could contribute to valuable endeavors, such as generating speech for individuals with aphasia or people with amyotrophic lateral sclerosis. See https://aka.ms/valle2 for demos of VALL-E 2.
Code (0)
등록된 구현이 없습니다.
Tasks
Speech Synthesistext-to-speechText to SpeechText-To-Speech SynthesisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling
We propose a cross-lingual neural codec language model, VALL-E X, for cross-lingual speech synthesis. Specifically, we extend VALL-E and train a multi-lingual conditional codec language model to predict the acoustic toke…
In-Context LearningLanguage ModelingLanguage ModellingSpeech Synthesis+4Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called Vall-E) using discrete codes derived from an off-the-shelf neural audio codec mod…
In-Context LearningLanguage ModelingLanguage ModellingSpeech Synthesis+3MIDI-VALLE: Improving Expressive Piano Performance Synthesis Through Neural Codec Language Modelling
Generating expressive audio performances from music scores requires models to capture both instrument acoustics and human interpretation. Traditional music performance synthesis pipelines follow a two-stage approach, fir…
Audio SynthesisLanguage Modellingtext-to-speechText to SpeechVALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment
With the help of discrete neural audio codecs, large language models (LLM) have increasingly been recognized as a promising methodology for zero-shot Text-to-Speech (TTS) synthesis. However, sampling based decoding strat…
QuantizationSpeech Synthesistext-to-speechText to Speech+1TacoLM: GaTed Attention Equipped Codec Language Model are Efficient Zero-Shot Text to Speech Synthesizers
Neural codec language model (LM) has demonstrated strong capability in zero-shot text-to-speech (TTS) synthesis. However, the codec LM often suffers from limitations in inference speed and stability, due to its auto-regr…
DecoderLanguage ModelingLanguage Modellingtext-to-speech+1