相关论文: Deep Transformer based Data Augmentation with Subw…

Automatic speech recognition (ASR) has improved substantially in recent years, yet performance remains limited for low-resource languages. Large language models (LLMs) have shown promise for improving ASR through generative error correction…

Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues as there exists little parallel S2ST data, compared to the amount of data available for conventional cascaded systems that consist of automatic speech…

Recent advances in text-to-speech (TTS) led to the development of flexible multi-speaker end-to-end TTS systems. We extend state-of-the-art attention-based automatic speech recognition (ASR) systems with synthetic audio generated by a TTS…

While integrating speech encoder with LLM requires substantial data and resources, use cases face limitations due to insufficient availability. To address this, we propose a solution with a parameter-efficient adapter that converts speech…

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…

Although contextualized automatic speech recognition (ASR) systems are commonly used to improve the recognition of uncommon words, their effectiveness is hindered by the inherent limitations of speech-text data availability. To address this…

The word error rate (WER) of an automatic speech recognition (ASR) system increases when a mismatch occurs between the training and the testing conditions due to the noise, etc. In this case, the acoustic information can be less reliable.…

We propose a method to automatically generate a domain- and task-adaptive maskings of the given text for self-supervised pre-training, such that we can effectively adapt the language model to a particular target task (e.g. question…

The success of speech assistants requires precise recognition of a number of entities on particular contexts. A common solution is to train a class-based n-gram language model and then expand the classes into specific words or phrases.…

This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories. The compute for pre-training LLMs has been growing at an…

Personal rare word recognition in end-to-end Automatic Speech Recognition (E2E ASR) models is a challenge due to the lack of training data. A standard way to address this issue is with shallow fusion methods at inference time. However, due…

In this progress paper the previous results of the single note recognition by deep learning are presented. The several ways for data augmentation and "artificial semantic" augmentation are proposed to enhance efficiency of deep learning…

As a cornerstone in language modeling, tokenization involves segmenting text inputs into pre-defined atomic units. Conventional statistical tokenizers often disrupt constituent boundaries within words, thereby corrupting semantic…

This paper explores the integration of Large Language Models (LLMs) into Automatic Speech Recognition (ASR) systems to improve transcription accuracy. The increasing sophistication of LLMs, with their in-context learning capabilities and…

We present a new end-to-end architecture for automatic speech recognition (ASR) that can be trained using \emph{symbolic} input in addition to the traditional acoustic input. This architecture utilizes two separate encoders: one for…

We develop a large language model (LLM) based automatic speech recognition (ASR) system that can be contextualized by providing keywords as prior information in text prompts. We adopt decoder-only architecture and use our in-house LLM,…

The effective incorporation of cross-utterance information has the potential to improve language models (LMs) for automatic speech recognition (ASR). To extract more powerful and robust cross-utterance representations for the Transformer LM…

This paper proposes a transformer over transformer framework, called Transformer$^2$, to perform neural text segmentation. It consists of two components: bottom-level sentence encoders using pre-trained transformers, and an upper-level…

Deep biasing for the Transducer can improve the recognition performance of rare words or contextual entities, which is essential in practical applications, especially for streaming Automatic Speech Recognition (ASR). However, deep biasing…

With the capabilities of understanding and executing natural language instructions, Large language models (LLMs) can potentially act as a powerful tool for textual data augmentation. However, the quality of augmented data depends heavily on…