On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition
The rapid development of neural text-to-speech (TTS) systems enabled its usage in other areas of natural language processing such as automatic speech recognition (ASR) or spoken language translation (SLT). Due to the large number of different TTS architectures and their extensions, selecting which TTS systems to use for synthetic data creation is not an easy task. We use the comparison of five different TTS decoder architectures in the scope of synthetic data generation to show the impact on CTC-based speech recognition training. We compare the recognition results to computable metrics like NISQA MOS and intelligibility, finding that there are no clear relations to the ASR performance. We also observe that for data generation auto-regressive decoding performs better than non-autoregressive decoding, and propose an approach to quantify TTS generalization capabilities.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderModel Selectionspeech-recognitionSpeech RecognitionSynthetic Data Generationtext-to-speechText to SpeechSimilar Papers 제목 키워드 기반
Scaling phoneme-based TTS augmentation for ASR: A unified pipeline and controlled study
Synthetic speech offers scalable supervision for automatic speech recognition (ASR), but its benefit depends on text selection, reference speech, and augmentation scale. We present a phoneme-based TTS-to-ASR pipeline usi…
Speech RecognitionText is All You Need: Personalizing ASR Models using Controllable Speech Synthesis
Adapting generic speech recognition models to specific individuals is a challenging problem due to the scarcity of personalized data. Recent works have proposed boosting the amount of training data using personalized tex…
AllAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognition+5Towards Selection of Text-to-speech Data to Augment ASR Training
This paper presents a method for selecting appropriate synthetic speech samples from a given large text-to-speech (TTS) dataset as supplementary training data for an automatic speech recognition (ASR) model. We trained a…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+2METTS: Multilingual Emotional Text-to-Speech by Cross-speaker and Cross-lingual Emotion Transfer
Previous multilingual text-to-speech (TTS) approaches have considered leveraging monolingual speaker data to enable cross-lingual speech synthesis. However, such data-efficient approaches have ignored synthesizing emotio…
DisentanglementDiversityQuantizationSpeech Synthesis+2Augmented Prompt Selection for Evaluation of Spontaneous Speech Synthesis
By definition, spontaneous speech is unscripted and created on the fly by the speaker. It is dramatically different from read speech, where the words are authored as text before they are spoken. Spontaneous speech is eme…
Speech Synthesis