On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition

• URL: http://arxiv.org/abs/2407.21476v1
• Date: Wed, 31 Jul 2024 09:37:27 GMT
• Title: On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition
• Authors: Nick Rossenbach, Ralf Schlüter, Sakriani Sakti,
• Abstract summary: We compare five different TTS decoder architectures in the scope of synthetic data generation to show the impact on CTC-based speech recognition training. For data generation auto-regressive decoding performs better than non-autoregressive decoding, and propose an approach to quantify TTS generalization capabilities.
• Score: 31.58289343561422
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM [48.71951982716363]
  Text-to-speech (TTS) models have been widely adopted to enhance automatic speech recognition (ASR) systems. We propose Hard- Synth, a novel ASR data augmentation method that leverages large language models (LLMs) and advanced zero-shot TTS. Our approach employs LLMs to generate diverse in-domain text through rewriting, without relying on additional text data.
  arXiv  Detail & Related papers  (2024-11-20T09:49:37Z)
• Large Generative Model-assisted Talking-face Semantic Communication System [55.42631520122753]
  This study introduces a Large Generative Model-assisted Talking-face Semantic Communication (LGM-TSC) system. Generative Semantic Extractor (GSE) at the transmitter converts semantically sparse talking-face videos into texts with high information density. Private Knowledge Base (KB) based on the Large Language Model (LLM) for semantic disambiguation and correction. Generative Semantic Reconstructor (GSR) that utilizes BERT-VITS2 and SadTalker models to transform text back into a high-QoE talking-face video.
  arXiv  Detail & Related papers  (2024-11-06T12:45:46Z)
• SONAR: A Synthetic AI-Audio Detection Framework and Benchmark [59.09338266364506]
  SONAR is a synthetic AI-Audio Detection Framework and Benchmark. It aims to provide a comprehensive evaluation for distinguishing cutting-edge AI-synthesized auditory content. It is the first framework to uniformly benchmark AI-audio detection across both traditional and foundation model-based deepfake detection systems.
  arXiv  Detail & Related papers  (2024-10-06T01:03:42Z)
• On the Effect of Purely Synthetic Training Data for Different Automatic Speech Recognition Architectures [19.823015917720284]
  We evaluate the utility of synthetic data for training automatic speech recognition. We reproduce the original training data, training ASR systems solely on synthetic data. We show that the TTS models generalize well, even when training scores indicate overfitting.
  arXiv  Detail & Related papers  (2024-07-25T12:44:45Z)
• On the Relevance of Phoneme Duration Variability of Synthesized Training Data for Automatic Speech Recognition [0.552480439325792]
  We focus on the temporal structure of synthetic data and its relation to ASR training. We show how much the degradation of synthetic data quality is influenced by duration modeling in non-autoregressive TTS. Using a simple algorithm we shift phoneme duration distributions of the TTS system closer to real durations.
  arXiv  Detail & Related papers  (2023-10-12T08:45:21Z)
• Towards Selection of Text-to-speech Data to Augment ASR Training [20.115236045164355]
  We train a neural network to measure the similarity of a synthetic data to real speech. We find that incorporating synthetic samples with considerable dissimilarity to real speech is crucial for boosting recognition performance.
  arXiv  Detail & Related papers  (2023-05-30T17:24:28Z)
• Code-Switching Text Generation and Injection in Mandarin-English ASR [57.57570417273262]
  We investigate text generation and injection for improving the performance of an industry commonly-used streaming model, Transformer-Transducer (T-T) We first propose a strategy to generate code-switching text data and then investigate injecting generated text into T-T model explicitly by Text-To-Speech (TTS) conversion or implicitly by tying speech and text latent spaces. Experimental results on the T-T model trained with a dataset containing 1,800 hours of real Mandarin-English code-switched speech show that our approaches to inject generated code-switching text significantly boost the performance of T-T models.
  arXiv  Detail & Related papers  (2023-03-20T09:13:27Z)
• A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech [94.64927912924087]
  We train TTS systems using real-world speech from YouTube and podcasts. Recent Text-to-Speech architecture is designed for multiple code generation and monotonic alignment. We show thatRecent Text-to-Speech architecture outperforms existing TTS systems in several objective and subjective measures.
  arXiv  Detail & Related papers  (2023-02-08T17:34:32Z)
• GraphSpeech: Syntax-Aware Graph Attention Network For Neural Speech Synthesis [79.1885389845874]
  Transformer-based end-to-end text-to-speech synthesis (TTS) is one of such successful implementations. We propose a novel neural TTS model, denoted as GraphSpeech, that is formulated under graph neural network framework. Experiments show that GraphSpeech consistently outperforms the Transformer TTS baseline in terms of spectrum and prosody rendering of utterances.
  arXiv  Detail & Related papers  (2020-10-23T14:14:06Z)

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.