相关论文: Methods of Automatic Matrix Language Determination…

Automatic spoken language identification (LID) is a very important research field in the era of multilingual voice-command-based human-computer interaction (HCI). A front-end LID module helps to improve the performance of many speech-based…

Code-switching automatic speech recognition (ASR) aims to transcribe speech that contains two or more languages accurately. To better capture language-specific speech representations and address language confusion in code-switching ASR, the…

In recent years, end-to-end speech recognition has emerged as a technology that integrates the acoustic, pronunciation dictionary, and language model components of the traditional Automatic Speech Recognition model. It is possible to…

Code-switching (CS), the alternating use of two or more languages, challenges automatic speech recognition (ASR) due to scarce training data and linguistic similarities. The lack of dedicated CS datasets limits ASR performance, as most…

In this work, we study whether multilingual language models (MultiLMs) can transfer logical reasoning abilities to other languages when they are fine-tuned for reasoning in a different language. We evaluate the cross-lingual reasoning…

Code-switching (CS), a ubiquitous phenomenon due to the ease of communication it offers in multilingual communities still remains an understudied problem in language processing. The primary reasons behind this are: (1) minimal efforts in…

Multilingual Large Language Models (LLMs) can process many languages, yet how they internally represent this diversity remains unclear. Do they form shared multilingual representations with language-specific decoding, and if so, why does…

Internal Language Model Estimation (ILME) based language model (LM) fusion has been shown significantly improved recognition results over conventional shallow fusion in both intra-domain and cross-domain speech recognition tasks. In this…

Code-switching speech recognition (CSSR) transcribes speech that switches between multiple languages or dialects within a single sentence. The main challenge in this task is that different languages often have similar pronunciations, making…

Code-switching automatic speech recognition (CS-ASR) presents unique challenges due to language confusion introduced by spontaneous intra-sentence switching and accent bias that blurs the phonetic boundaries. Although the constituent…

State-of-the-art spoken language identification (LID) systems, which are based on end-to-end deep neural networks, have shown remarkable success not only in discriminating between distant languages but also between closely-related languages…

Informal transliteration from other languages to English is prevalent in social media threads, instant messaging, and discussion forums. Without identifying the language of such transliterated text, users who do not speak that language…

Recently, there has been significant progress made in Automatic Speech Recognition (ASR) of code-switched speech, leading to gains in accuracy on code-switched datasets in many language pairs. Code-switched speech co-occurs with monolingual…

Large Language Models (LLMs) have impressive multilingual capabilities, but they suffer from unexpected code-switching, also known as language mixing, which involves switching to unexpected languages in the model response. This problem…

Recently, language identity information has been utilized to improve the performance of end-to-end code-switching (CS) speech recognition. However, previous works use an additional language identification (LID) model as an auxiliary module,…

In this paper, we introduce a speech-conditioned Large Language Model (LLM) integrated with a Mixture of Experts (MoE) based connector to address the challenge of Code-Switching (CS) in Automatic Speech Recognition (ASR). Specifically, we…

In multilingual colloquial settings, it is a habitual occurrence to compose expressions of text or speech containing tokens or phrases of different languages, a phenomenon popularly known as code-switching or code-mixing (CMX). We present…

This paper introduces and motivates the use of hybrid robust feature extraction technique for spoken language identification (LID) system. The speech recognizers use a parametric form of a signal to get the most important distinguishable…

Large language models (LLMs) exhibit remarkable multilingual capabilities despite the extreme language imbalance in the pre-training data. In this paper, we closely examine the reasons behind this phenomenon, focusing on the pre-training…

Large language models (LLMs) now exhibit near human-level performance in various tasks, but their performance drops drastically after a handful of high-resource languages due to the imbalance in pre-training data. Inspired by the human…