相关论文: Adapting Multi-Lingual ASR Models for Handling Mul…

Multilingual end-to-end models have shown great improvement over monolingual systems. With the development of pre-training methods on speech, self-supervised multilingual speech representation learning like XLSR has shown success in…

Human language is a combination of elemental languages/domains/styles that change across and sometimes within discourses. Language models, which play a crucial role in speech recognizers and machine translation systems, are particularly…

Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…

Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however, additional context, such as the time at which an utterance…

This paper describes noisy speech recognition for an augmented reality headset that helps verbal communication within real multiparty conversational environments. A major approach that has actively been studied in simulated environments is…

Recent work shows promising results in expanding the capabilities of large language models (LLM) to directly understand and synthesize speech. However, an LLM-based strategy for modeling spoken dialogs remains elusive, calling for further…

Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two distinct large networks. We propose a parameter-efficient…

Speaker adaptation, which involves cloning voices from unseen speakers in the Text-to-Speech task, has garnered significant interest due to its numerous applications in multi-media fields. Despite recent advancements, existing methods often…

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…

This paper presents a newly developed, simultaneous neural speech-to-speech translation system and its evaluation. The system consists of three fully-incremental neural processing modules for automatic speech recognition (ASR), machine…

Multilingual models can improve language processing, particularly for low resource situations, by sharing parameters across languages. Multilingual acoustic models, however, generally ignore the difference between phonemes (sounds that can…

Advances in machine learning have made it possible to perform various text and speech processing tasks, such as automatic speech recognition (ASR), in an end-to-end (E2E) manner. E2E approaches utilizing pre-trained models are gaining…

Word-piece models (WPMs) are commonly used subword units in state-of-the-art end-to-end automatic speech recognition (ASR) systems. For multilingual ASR, due to the differences in written scripts across languages, multilingual WPMs bring…

In previous work, we developed a closed-loop speech chain model based on deep learning, in which the architecture enabled the automatic speech recognition (ASR) and text-to-speech synthesis (TTS) components to mutually improve their…

In this paper, we conduct a comparative study on speaker-attributed automatic speech recognition (SA-ASR) in the multi-party meeting scenario, a topic with increasing attention in meeting rich transcription. Specifically, three approaches…

An increasingly common training paradigm for multi-talker automatic speech recognition (ASR) is to use speaker activity signals to adapt single-speaker ASR models for overlapping speech. Although effective, these systems require running the…

Transferring the knowledge of large language models (LLMs) is a promising technique to incorporate linguistic knowledge into end-to-end automatic speech recognition (ASR) systems. However, existing works only transfer a single…

Speaker diarization is necessary for interpreting conversations transcribed using automated speech recognition (ASR) tools. Despite significant developments in diarization methods, diarization accuracy remains an issue. Here, we investigate…

Adapting pre-trained text Large Language Models (LLMs) into Speech Language Models (Speech LMs) via continual pretraining on speech data is promising, but often degrades the original text capabilities. We propose Multimodal Depth Upscaling,…

With the growing adoption of wearable devices such as smart glasses for AI assistants, wearer speech recognition (WSR) is becoming increasingly critical to next-generation human-computer interfaces. However, in real environments,…