Related papers: Twists, Humps, and Pebbles: Multilingual Speech Re…

A crucial part of an accurate and reliable spoken language assessment system is the underlying ASR model. Recently, large-scale pre-trained ASR foundation models such as Whisper have been made available. As the output of these models is…

Gender bias is largely recognized as a problematic phenomenon affecting language technologies, with recent studies underscoring that it might surface differently across languages. However, most of current evaluation practices adopt a…

Form about four decades human beings have been dreaming of an intelligent machine which can master the natural speech. In its simplest form, this machine should consist of two subsystems, namely automatic speech recognition (ASR) and speech…

Pre-trained transformer-based models have significantly advanced automatic speech recognition (ASR), yet they remain sensitive to accent and dialectal variations, resulting in elevated word error rates (WER) in linguistically diverse…

Large Audio-Language Models (LALMs) as judges have emerged as a prominent approach for evaluating speech generation quality, yet their ability to assess speaker consistency across multi-turn dialogues remains unexplored. We present…

Fine-tuning pretrained language models (LMs) is a popular approach to automatic speech recognition (ASR) error detection during post-processing. While error detection systems often take advantage of statistical language archetypes captured…

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…

Conversational speech normally is embodied with loose syntactic structures at the utterance level but simultaneously exhibits topical coherence relations across consecutive utterances. Prior work has shown that capturing longer context…

While research on applications and evaluations of explanation methods continues to expand, fairness of the explanation methods concerning disparities in their performance across subgroups remains an often overlooked aspect. In this paper,…

Automatic Speech Recognition (ASR) systems often struggle with transcribing child speech due to the lack of large child speech datasets required to accurately train child-friendly ASR models. However, there are huge amounts of annotated…

Automatic speech recognition (ASR) outcomes serve as input for downstream tasks, substantially impacting the satisfaction level of end-users. Hence, the diagnosis and enhancement of the vulnerabilities present in the ASR model bear…

The idea of combining multiple languages' recordings to train a single automatic speech recognition (ASR) model brings the promise of the emergence of universal speech representation. Recently, a Transformer encoder-decoder model has been…

Multilingual representations embed words from many languages into a single semantic space such that words with similar meanings are close to each other regardless of the language. These embeddings have been widely used in various settings,…

This paper presents a brief survey on Automatic Speech Recognition and discusses the major themes and advances made in the past 60 years of research, so as to provide a technological perspective and an appreciation of the fundamental…

Speech Integrated Large Language Models (SILLMs) combine large language models with speech perception to perform diverse tasks, such as emotion recognition to speaker verification, demonstrating universal audio understanding capability.…

The quality of automatic speech recognition (ASR) is critical to Dialogue Systems as ASR errors propagate to and directly impact downstream tasks such as language understanding (LU). In this paper, we propose multi-task neural approaches to…

This paper presents an audio visual automatic speech recognition (AV-ASR) system using a Transformer-based architecture. We particularly focus on the scene context provided by the visual information, to ground the ASR. We extract…

How much audio is needed to fully observe a multilingual ASR model's learned sub-token inventory across languages, and does data disparity in multilingual pre-training affect how these tokens are utilized during inference? We address this…

Discrete speech representations have garnered recent attention for their efficacy in training transformer-based models for various speech-related tasks such as automatic speech recognition (ASR), translation, speaker verification, and joint…

Language models (LMs) have become pivotal in the realm of technological advancements. While their capabilities are vast and transformative, they often include societal biases encoded in the human-produced datasets used for their training.…