Transcript-Prompted Whisper with Dictionary-Enhanced Decoding for Japanese Speech Annotation

• URL: http://arxiv.org/abs/2506.07646v1
• Date: Mon, 09 Jun 2025 11:10:24 GMT
• Title: Transcript-Prompted Whisper with Dictionary-Enhanced Decoding for Japanese Speech Annotation
• Authors: Rui Hu, Xiaolong Lin, Jiawang Liu, Shixi Huang, Zhenpeng Zhan,
• Abstract summary: We propose a method for annotating phonemic and prosodic labels on a given audio-transcript pair.<n>We employ a decoding strategy that utilizes dictionary prior knowledge to correct errors in phonemic labeling.<n>The subjective evaluation results indicate that the naturalness of speech synthesized by the TTS model, trained with labels annotated using our method, is comparable to that of a model trained with manual annotations.
• Score: 4.314729314139958
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we propose a method for annotating phonemic and prosodic labels on a given audio-transcript pair, aimed at constructing Japanese text-to-speech (TTS) datasets. Our approach involves fine-tuning a large-scale pre-trained automatic speech recognition (ASR) model, conditioned on ground truth transcripts, to simultaneously output phrase-level graphemes and annotation labels. To further correct errors in phonemic labeling, we employ a decoding strategy that utilizes dictionary prior knowledge. The objective evaluation results demonstrate that our proposed method outperforms previous approaches relying solely on text or audio. The subjective evaluation results indicate that the naturalness of speech synthesized by the TTS model, trained with labels annotated using our method, is comparable to that of a model trained with manual annotations.

Related papers

• Grapheme-Coherent Phonemic and Prosodic Annotation of Speech by Implicit and Explicit Grapheme Conditioning [9.413818055887763]
  We propose a model to obtain phonemic and prosodic labels of speech that are coherent with graphemes.<n> Experiments showed that the proposed method significantly improved the consistency between graphemes and the predicted labels.
  arXiv  Detail & Related papers  (2025-06-05T00:24:00Z)
• Automatic Text Pronunciation Correlation Generation and Application for Contextual Biasing [17.333427709985376]
  We propose a data-driven method to automatically acquire pronunciation correlations, called automatic text pronunciation correlation (ATPC)<n> Experimental results on Mandarin show that ATPC enhances E2E-ASR performance in contextual biasing.
  arXiv  Detail & Related papers  (2025-01-01T11:10:46Z)
• Zero-shot text-to-speech synthesis conditioned using self-supervised speech representation model [13.572330725278066]
  A novel point of the proposed method is the direct use of the SSL model to obtain embedding vectors from speech representations trained with a large amount of data. The disentangled embeddings will enable us to achieve better reproduction performance for unseen speakers and rhythm transfer conditioned by different speeches.
  arXiv  Detail & Related papers  (2023-04-24T10:15:58Z)
• SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training [106.34112664893622]
  We propose a unified-modal speech-unit-text pre-training model, SpeechUT, to connect the representations of a speech encoder and a text decoder with a shared unit encoder. Our proposed SpeechUT is fine-tuned and evaluated on automatic speech recognition (ASR) and speech translation (ST) tasks.
  arXiv  Detail & Related papers  (2022-10-07T17:57:45Z)
• 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)
• Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speech [88.22544315633687]
  Polyphone disambiguation aims to capture accurate pronunciation knowledge from natural text sequences for reliable Text-to-speech systems. We propose Dict-TTS, a semantic-aware generative text-to-speech model with an online website dictionary. Experimental results in three languages show that our model outperforms several strong baseline models in terms of pronunciation accuracy.
  arXiv  Detail & Related papers  (2022-06-05T10:50:34Z)
• Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages [58.43299730989809]
  We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech recognition task. This process stands on its own, or can be applied as low-cost second-stage pre-training.
  arXiv  Detail & Related papers  (2022-05-02T17:59:02Z)
• Word Order Does Not Matter For Speech Recognition [35.96275156733138]
  We train a word-level acoustic model which aggregates the distribution of all output frames. We then train a letter-based acoustic model using Connectionist Temporal Classification loss. Our system achieves 2.4%/5.3% on test-clean/test-other subsets of LibriSpeech.
  arXiv  Detail & Related papers  (2021-10-12T13:35:01Z)
• Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration [62.75234183218897]
  We propose a one-stage context-aware framework to generate natural and coherent target speech without any training data of the speaker. We generate the mel-spectrogram of the edited speech with a transformer-based decoder. It outperforms a recent zero-shot TTS engine by a large margin.
  arXiv  Detail & Related papers  (2021-09-12T04:17:53Z)
• Direct speech-to-speech translation with discrete units [64.19830539866072]
  We present a direct speech-to-speech translation (S2ST) model that translates speech from one language to speech in another language without relying on intermediate text generation. We propose to predict the self-supervised discrete representations learned from an unlabeled speech corpus instead. When target text transcripts are available, we design a multitask learning framework with joint speech and text training that enables the model to generate dual mode output (speech and text) simultaneously in the same inference pass.
  arXiv  Detail & Related papers  (2021-07-12T17:40:43Z)

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.