Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP

• URL: http://arxiv.org/abs/2309.05423v2
• Date: Tue, 11 Jun 2024 16:43:11 GMT
• Title: Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP
• Authors: Jinzuomu Zhong, Yang Li, Hui Huang, Korin Richmond, Jie Liu, Zhiba Su, Jing Guo, Benlai Tang, Fengjie Zhu,
• Abstract summary: A two-stage automatic annotation pipeline is proposed in this paper. In the first stage, we use contrastive pretraining of Speech-Silence and Word-Punctuation pairs to enhance prosodic information in latent representations. In the second stage, we build a multi-modal prosody annotator, comprising pretrained encoders, a text-speech fusing scheme, and a sequence classifier. Experiments on English prosodic boundaries demonstrate that our method achieves state-of-the-art (SOTA) performance with 0.72 and 0.93 f1 score for Prosodic Word and Prosodic Phrase
• Score: 18.90593650641679
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In expressive and controllable Text-to-Speech (TTS), explicit prosodic features significantly improve the naturalness and controllability of synthesised speech. However, manual prosody annotation is labor-intensive and inconsistent. To address this issue, a two-stage automatic annotation pipeline is novelly proposed in this paper. In the first stage, we use contrastive pretraining of Speech-Silence and Word-Punctuation (SSWP) pairs to enhance prosodic information in latent representations. In the second stage, we build a multi-modal prosody annotator, comprising pretrained encoders, a text-speech fusing scheme, and a sequence classifier. Experiments on English prosodic boundaries demonstrate that our method achieves state-of-the-art (SOTA) performance with 0.72 and 0.93 f1 score for Prosodic Word and Prosodic Phrase boundary respectively, while bearing remarkable robustness to data scarcity.

Related papers

• 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)
• Improving Mandarin Prosodic Structure Prediction with Multi-level Contextual Information [68.89000132126536]
  This work proposes to use inter-utterance linguistic information to improve the performance of prosodic structure prediction (PSP) Our method achieves better F1 scores in predicting prosodic word (PW), prosodic phrase (PPH) and intonational phrase (IPH)
  arXiv  Detail & Related papers  (2023-08-31T09:19:15Z)
• token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text [65.04385919645395]
  token2vec is a novel joint pre-training framework for unpaired speech and text based on discrete representations of speech. Experiments show that token2vec is significantly superior to various speech-only pre-training baselines, with up to 17.7% relative WER reduction.
  arXiv  Detail & Related papers  (2022-10-30T06:38:19Z)
• Automatic Prosody Annotation with Pre-Trained Text-Speech Model [48.47706377700962]
  We propose to automatically extract prosodic boundary labels from text-audio data via a neural text-speech model with pre-trained audio encoders. This model is pre-trained on text and speech data separately and jointly fine-tuned on TTS data in a triplet format: speech, text, prosody
  arXiv  Detail & Related papers  (2022-06-16T06:54:16Z)
• 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)
• ProsoSpeech: Enhancing Prosody With Quantized Vector Pre-training in Text-to-Speech [96.0009517132463]
  We introduce a word-level prosody encoder, which quantizes the low-frequency band of the speech and compresses prosody attributes in the latent prosody vector (LPV) We then introduce an LPV predictor, which predicts LPV given word sequence and fine-tune it on the high-quality TTS dataset. Experimental results show that ProsoSpeech can generate speech with richer prosody compared with baseline methods.
  arXiv  Detail & Related papers  (2022-02-16T01:42:32Z)
• Improving Prosody for Unseen Texts in Speech Synthesis by Utilizing Linguistic Information and Noisy Data [20.132799566988826]
  We propose to combine a fine-tuned BERT-based front-end with a pre-trained FastSpeech2-based acoustic model to improve prosody modeling. Experimental results show that both the fine-tuned BERT model and the pre-trained FastSpeech 2 can improve prosody, especially for those structurally complex sentences.
  arXiv  Detail & Related papers  (2021-11-15T05:58:29Z)
• SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training [33.02912456062474]
  We build a single encoder with the BERT objective on unlabeled text together with the w2v-BERT objective on unlabeled speech. We demonstrate that incorporating both speech and text data during pre-training can significantly improve downstream quality on CoVoST2 speech translation.
  arXiv  Detail & Related papers  (2021-10-20T00:59:36Z)
• Improving Prosody Modelling with Cross-Utterance BERT Embeddings for End-to-end Speech Synthesis [39.869097209615724]
  Cross-utterance (CU) context vectors are produced by an additional CU encoder based on the sentence embeddings extracted by a pre-trained BERT model. It is also found that the prosody can be controlled indirectly by changing the neighbouring sentences.
  arXiv  Detail & Related papers  (2020-11-06T10:03:11Z)

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.