Related papers: Streaming Language Identification using Combinatio…

Automatic Speech Recognition (ASR), as the assistance of speech communication between pilots and air-traffic controllers, can significantly reduce the complexity of the task and increase the reliability of transmitted information. ASR…

Under noisy conditions, automatic speech recognition (ASR) can greatly benefit from the addition of visual signals coming from a video of the speaker's face. However, when multiple candidate speakers are visible this traditionally requires…

Sequence-to-sequence models provide a simple and elegant solution for building speech recognition systems by folding separate components of a typical system, namely acoustic (AM), pronunciation (PM) and language (LM) models into a single…

Recognizing overlapping speech from multiple speakers in conversational scenarios is one of the most challenging problem for automatic speech recognition (ASR). Serialized output training (SOT) is a classic method to address multi-talker…

Text to speech (TTS) and automatic speech recognition (ASR) are two dual tasks in speech processing and both achieve impressive performance thanks to the recent advance in deep learning and large amount of aligned speech and text data.…

Audio is the primary modality for human communication and has driven the success of Automatic Speech Recognition (ASR) technologies. However, such audio-centric systems inherently exclude individuals who are deaf or hard of hearing. Visual…

Multimodal speech recognition aims to improve the performance of automatic speech recognition (ASR) systems by leveraging additional visual information that is usually associated to the audio input. While previous approaches make crucial…

Only a handful of the world's languages are abundant with the resources that enable practical applications of speech processing technologies. One of the methods to overcome this problem is to use the resources existing in other languages to…

For real-world speech recognition applications, noise robustness is still a challenge. In this work, we adopt the teacher-student (T/S) learning technique using a parallel clean and noisy corpus for improving automatic speech recognition…

Large Language Model (LLM)-powered Automatic Speech Recognition (ASR) systems achieve strong performance with limited resources by linking a frozen speech encoder to a pretrained LLM via a lightweight connector. Prior work trains a separate…

Multilingual Automatic Speech Recognition (ASR) models are typically evaluated in a setting where the ground-truth language of the speech utterance is known, however, this is often not the case for most practical settings. Automatic Spoken…

This paper presents a speech intelligibility model based on automatic speech recognition (ASR), combining phoneme probabilities from deep neural networks (DNN) and a performance measure that estimates the word error rate from these…

In this paper, we describe several techniques for improving the acoustic and language model of an automatic speech recognition (ASR) system operating on code-switching (CS) speech. We focus on the recognition of Frisian-Dutch radio…

Speaker identification in multilingual settings presents unique challenges, particularly when conventional models are predominantly trained on English data. In this paper, we propose WSI (Whisper Speaker Identification), a framework that…

Multi-speaker speech recognition of unsegmented recordings has diverse applications such as meeting transcription and automatic subtitle generation. With technical advances in systems dealing with speech separation, speaker diarization, and…

Multilingual speech processing with self-supervised or supervised pre-trained Speech Foundation Models (SFM) has achieved strong performance on tasks like Language Identification (LID) and Automatic Speech Recognition (ASR). However, these…

Collecting sufficient labeled data for spoken language understanding (SLU) is expensive and time-consuming. Recent studies achieved promising results by using pre-trained models in low-resource scenarios. Inspired by this, we aim to ask:…

This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by transfer learning from…

Self-supervised learning (SSL), which utilizes the input data itself for representation learning, has achieved state-of-the-art results for various downstream speech tasks. However, most of the previous studies focused on offline…

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…