Utilizing Neural Transducers for Two-Stage Text-to-Speech via Semantic Token Prediction

• URL: http://arxiv.org/abs/2401.01498v1
• Date: Wed, 3 Jan 2024 02:03:36 GMT
• Title: Utilizing Neural Transducers for Two-Stage Text-to-Speech via Semantic Token Prediction
• Authors: Minchan Kim, Myeonghun Jeong, Byoung Jin Choi, Semin Kim, Joun Yeop Lee, Nam Soo Kim
• Abstract summary: We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages. Our experimental results on zero-shot adaptive TTS demonstrate that our model surpasses the baseline in terms of speech quality and speaker similarity.
• Score: 15.72317249204736
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages, utilizing discrete semantic tokens obtained from wav2vec2.0 embeddings. For a robust and efficient alignment modeling, we employ a neural transducer named token transducer for the semantic token prediction, benefiting from its hard monotonic alignment constraints. Subsequently, a non-autoregressive (NAR) speech generator efficiently synthesizes waveforms from these semantic tokens. Additionally, a reference speech controls temporal dynamics and acoustic conditions at each stage. This decoupled framework reduces the training complexity of TTS while allowing each stage to focus on semantic and acoustic modeling. Our experimental results on zero-shot adaptive TTS demonstrate that our model surpasses the baseline in terms of speech quality and speaker similarity, both objectively and subjectively. We also delve into the inference speed and prosody control capabilities of our approach, highlighting the potential of neural transducers in TTS frameworks.

Related papers

• CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens [49.569695524535454]
  We propose to represent speech with supervised semantic tokens, which are derived from a multilingual speech recognition model by inserting vector quantization into the encoder. Based on the tokens, we further propose a scalable zero-shot TTS synthesizer, CosyVoice, which consists of an LLM for text-to-token generation and a conditional flow matching model for token-to-speech synthesis.
  arXiv  Detail & Related papers  (2024-07-07T15:16:19Z)
• Transduce and Speak: Neural Transducer for Text-to-Speech with Semantic Token Prediction [14.661123738628772]
  We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic alignment constraints.
  arXiv  Detail & Related papers  (2023-11-06T06:13:39Z)
• High-Fidelity Speech Synthesis with Minimal Supervision: All Using Diffusion Models [56.00939852727501]
  Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech representations. Non-autoregressive framework enhances controllability, and duration diffusion model enables diversified prosodic expression.
  arXiv  Detail & Related papers  (2023-09-27T09:27:03Z)
• Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias [71.94109664001952]
  Mega-TTS is a novel zero-shot TTS system that is trained with large-scale wild data. We show that Mega-TTS surpasses state-of-the-art TTS systems on zero-shot TTS speech editing, and cross-lingual TTS tasks.
  arXiv  Detail & Related papers  (2023-06-06T08:54:49Z)
• Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAE [36.50265124324876]
  We propose a novel unsupervised text-to-speech acoustic model training scheme, named UTTS, which does not require text-audio pairs. The framework offers a flexible choice of a speaker's duration model, timbre feature (identity) and content for TTS inference. Experiments demonstrate that UTTS can synthesize speech of high naturalness and intelligibility measured by human and objective evaluations.
  arXiv  Detail & Related papers  (2022-06-06T11:51:22Z)
• TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation [61.564874831498145]
  TranSpeech is a speech-to-speech translation model with bilateral perturbation. We establish a non-autoregressive S2ST technique, which repeatedly masks and predicts unit choices. TranSpeech shows a significant improvement in inference latency, enabling speedup up to 21.4x than autoregressive technique.
  arXiv  Detail & Related papers  (2022-05-25T06:34:14Z)
• Emphasis control for parallel neural TTS [8.039245267912511]
  The semantic information conveyed by a speech signal is strongly influenced by local variations in prosody. Recent parallel neural text-to-speech (TTS) methods are able to generate speech with high fidelity while maintaining high performance. This paper proposes a hierarchical parallel neural TTS system for prosodic emphasis control by learning a latent space that directly corresponds to a change in emphasis.
  arXiv  Detail & Related papers  (2021-10-06T18:45:39Z)
• Advances in Speech Vocoding for Text-to-Speech with Continuous Parameters [2.6572330982240935]
  This paper presents new techniques in a continuous vocoder, that is all features are continuous and presents a flexible speech synthesis system. New continuous noise masking based on the phase distortion is proposed to eliminate the perceptual impact of the residual noise. Bidirectional long short-term memory (LSTM) and gated recurrent unit (GRU) are studied and applied to model continuous parameters for more natural-sounding like a human.
  arXiv  Detail & Related papers  (2021-06-19T12:05:01Z)
• Pretraining Techniques for Sequence-to-Sequence Voice Conversion [57.65753150356411]
  Sequence-to-sequence (seq2seq) voice conversion (VC) models are attractive owing to their ability to convert prosody. We propose to transfer knowledge from other speech processing tasks where large-scale corpora are easily available, typically text-to-speech (TTS) and automatic speech recognition (ASR) We argue that VC models with such pretrained ASR or TTS model parameters can generate effective hidden representations for high-fidelity, highly intelligible converted speech.
  arXiv  Detail & Related papers  (2020-08-07T11:02:07Z)
• DiscreTalk: Text-to-Speech as a Machine Translation Problem [52.33785857500754]
  This paper proposes a new end-to-end text-to-speech (E2E-TTS) model based on neural machine translation (NMT) The proposed model consists of two components; a non-autoregressive vector quantized variational autoencoder (VQ-VAE) model and an autoregressive Transformer-NMT model.
  arXiv  Detail & Related papers  (2020-05-12T02:45:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.