相关论文: Hard-Synth: Synthesizing Diverse Hard Samples for …

Automatic speech recognition (ASR) systems have achieved strong performance on general transcription tasks. However, they continue to struggle with recognizing rare named entities and adapting to domain mismatches. In contrast, large…

Building an accurate automatic speech recognition (ASR) system requires a large dataset that contains many hours of labeled speech samples produced by a diverse set of speakers. The lack of such open free datasets is one of the main issues…

This paper proposes an automatic speech recognition (ASR) model for hate speech using large language models (LLMs). The proposed method integrates the encoder of the ASR model with the decoder of the LLMs, enabling simultaneous…

The performance of automatic speech recognition (ASR) systems has advanced substantially in recent years, particularly for languages for which a large amount of transcribed speech is available. Unfortunately, for low-resource languages,…

Recent advances in generative language modeling applied to discrete speech tokens presented a new avenue for text-to-speech (TTS) synthesis. These speech language models (SLMs), similarly to their textual counterparts, are scalable,…

Automatic speech recognition (ASR) models rely on high-quality transcribed data for effective training. Generating pseudo-labels for large unlabeled audio datasets often relies on complex pipelines that combine multiple ASR outputs through…

This paper proposes a GRPO-based approach to enhance the performance of large language model (LLM)-based text-to-speech (TTS) models by deriving rewards from an off-the-shelf automatic speech recognition (ASR) model. Compared to previous…

In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model size scaling, and deep integration with large language models (LLMs). However, LLMs…

Automatic Speech Recognition (ASR) has recently shown remarkable progress, but accurately transcribing children's speech remains a significant challenge. Recent developments in Large Language Models (LLMs) have shown promise in improving…

In recent years, several text-to-speech systems have been proposed to synthesize natural speech in zero-shot, few-shot, and low-resource scenarios. However, these methods typically require training with data from many different speakers.…

With the help of discrete neural audio codecs, large language models (LLM) have increasingly been recognized as a promising methodology for zero-shot Text-to-Speech (TTS) synthesis. However, sampling based decoding strategies bring…

Recent advancement in deep learning encouraged developing large automatic speech recognition (ASR) models that achieve promising results while ignoring computational and memory constraints. However, deploying such models on low resource…

In this paper we study the impact of augmenting spoken language corpora with domain-specific synthetic samples for the purpose of training a speech recognition system. Using both a conventional neural TTS system and a zero-shot one with…

In this study, we investigate the integration of a large language model (LLM) with an automatic speech recognition (ASR) system, specifically focusing on enhancing rare word recognition performance. Using a 190,000-hour dataset primarily…

Despite extensions to speech inputs, effectively leveraging the rich knowledge and contextual understanding of large language models (LLMs) in automatic speech recognition (ASR) remains non-trivial, as the task primarily involves direct…

Speech-enabled systems typically first convert audio to text through an automatic speech recognition (ASR) model and then feed the text to downstream natural language processing (NLP) modules. The errors of the ASR system can seriously…

Automatic Speech Recognition (ASR) systems are pivotal in transcribing speech into text, yet the errors they introduce can significantly degrade the performance of downstream tasks like summarization. This issue is particularly pronounced…

While neural text-to-speech (TTS) has achieved human-like natural synthetic speech, multilingual TTS systems are limited to resource-rich languages due to the need for paired text and studio-quality audio data. This paper proposes a method…

In this work, we take on the challenging task of building a single text-to-speech synthesis system that is capable of generating speech in over 7000 languages, many of which lack sufficient data for traditional TTS development. By…

Adapting large language model (LLM)-based automatic speech recognition (ASR) systems to new domains using text-only data is a significant yet underexplored challenge. Standard fine-tuning of the LLM on the target domain text often disrupts…