Related papers: Towards One Model to Rule All: Multilingual Strate…
A major focus of recent research in spoken language understanding (SLU) has been on the end-to-end approach where a single model can predict intents directly from speech inputs without intermediate transcripts. However, this approach…
Automated Speech Recognition (ASR) is an interdisciplinary application of computer science and linguistics that enable us to derive the transcription from the uttered speech waveform. It finds several applications in Military like…
ASR has achieved remarkable global progress, yet African low-resource languages remain rigorously underrepresented, producing barriers to digital inclusion across the continent with more than +2000 languages. This systematic literature…
Code-switching (CS), common in multilingual settings, presents challenges for ASR due to scarce and costly transcribed data caused by linguistic complexity. This study investigates building CS-ASR using synthetic CS data. We propose a…
We present an analysis of diacritic recognition performance in Arabic Automatic Speech Recognition (ASR) systems. As most existing Arabic speech corpora do not contain all diacritical marks, which represent short vowels and other phonetic…
In this work, we propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems. The proposed model integrates the feature learning block,…
Multi-talker speech recognition (MT-ASR) has been shown to improve ASR performance on speech containing overlapping utterances from more than one speaker. Multi-talker models have typically been trained from scratch using simulated or…
Code-switching (CS) refers to the phenomenon that languages switch within a speech signal and leads to language confusion for automatic speech recognition (ASR). This paper aims to address language confusion for improving CS-ASR from two…
Large Language Models (LLMs) are becoming increasingly multilingual, supporting hundreds of languages, especially high resource ones. Unfortunately, Dialect variations are still underrepresented due to limited data and linguistic variation.…
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…
Speech to text models tend to be trained and evaluated against a single target accent. This is especially true for English for which native speakers from the United States became the main benchmark. In this work, we are going to show how…
Audio large language models (LLMs) enable unified speech understanding and generation, but adapting them to linguistically complex and dialect-rich settings such as Arabic-English remains challenging. We present a controlled study of…
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…
Automatic speech recognition (ASR) systems normally consist of an acoustic model (AM) and a language model (LM). The acoustic model estimates the probability distribution of text given the input speech, while the language model calibrates…
Automatic speech recognition (ASR) has advanced in high-resource languages, but most of the world's 7,000+ languages remain unsupported, leaving thousands of long-tail languages behind. Expanding ASR coverage has been costly and limited by…
This report introduces Dolphin, a large-scale multilingual automatic speech recognition (ASR) model that extends the Whisper architecture to support a wider range of languages. Our approach integrates in-house proprietary and open-source…
Arabic dialect identification (ADI) tools are an important part of the large-scale data collection pipelines necessary for training speech recognition models. As these pipelines require application of ADI tools to potentially out-of-domain…
This paper presents recent progress in the acoustic modelling of under-resourced code-switched (CS) speech in multiple South African languages. We consider two approaches. The first constructs separate bilingual acoustic models…
Off-the-shelf pre-trained Automatic Speech Recognition (ASR) systems are an increasingly viable service for companies of any size building speech-based products. While these ASR systems are trained on large amounts of data, domain mismatch…
In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel…