Related papers: Fast Development of ASR in African Languages using…
Automatic speech recognition (ASR) has been widely researched with supervised approaches, while many low-resourced languages lack audio-text aligned data, and supervised methods cannot be applied on them. In this work, we propose a…
Neural network pruning compresses automatic speech recognition (ASR) models effectively. However, in multilingual ASR, language-agnostic pruning may lead to severe performance drops on some languages because language-agnostic pruning masks…
Automatic Speech Recognition (ASR) has reached impressive accuracy for high-resource languages, yet its utility in linguistic fieldwork remains limited. Recordings collected in fieldwork contexts present unique challenges, including…
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…
Developing robust automatic speech recognition (ASR) systems for Arabic requires effective strategies to manage its diversity. Existing ASR systems mainly cover the modern standard Arabic (MSA) variety and few high-resource dialects, but…
This study presents an approach for collecting speech samples to build Automatic Speech Recognition (ASR) models for impaired speech, particularly, low-resource languages. It aims to democratize ASR technology and data collection by…
Self-supervised learning (SSL) based speech pre-training has attracted much attention for its capability of extracting rich representations learned from massive unlabeled data. On the other hand, the use of weakly-supervised data is less…
Recent advances in speech-enabled AI, including Google's NotebookLM and OpenAI's speech-to-speech API, are driving widespread interest in voice interfaces globally. Despite this momentum, there exists no publicly available…
Humans are capable of processing speech by making use of multiple sensory modalities. For example, the environment where a conversation takes place generally provides semantic and/or acoustic context that helps us to resolve ambiguities or…
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…
The machine recognition of speech spoken at a distance from the microphones, known as far-field automatic speech recognition (ASR), has received a significant increase of attention in science and industry, which caused or was caused by an…
Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds…
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.…
Large language model (LLM)-based automatic speech recognition (ASR) achieves strong performance but often incurs high computational costs. This work investigates how to obtain the best LLM-ASR performance efficiently. Through comprehensive…
With the advent of globalization, there is an increasing demand for multilingual automatic speech recognition (ASR), handling language and dialectal variation of spoken content. Recent studies show its efficacy over monolingual systems. In…
Automatic speech recognition (ASR) in Sanskrit is interesting, owing to the various linguistic peculiarities present in the language. The Sanskrit language is lexically productive, undergoes euphonic assimilation of phones at the word…
Large Language Models (LLMs) have showcased exceptional performance across diverse NLP tasks, and their integration with speech encoder is rapidly emerging as a dominant trend in the Automatic Speech Recognition (ASR) field. Previous works…
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…
In this work, we introduce a simple yet efficient post-processing model for automatic speech recognition (ASR). Our model has Transformer-based encoder-decoder architecture which "translates" ASR model output into grammatically and…
Spoken dialog systems are slowly becoming and integral part of the human experience due to their various advantages over textual interfaces. Spoken language understanding (SLU) systems are fundamental building blocks of spoken dialog…