Related papers: Improving Language Identification for Multilingual…

Language identification greatly impacts the success of downstream tasks such as automatic speech recognition. Recently, self-supervised speech representations learned by wav2vec 2.0 have been shown to be very effective for a range of speech…

Speaker identification, determining which character said each utterance in literary text, benefits many downstream tasks. Most existing approaches use expert-defined rules or rule-based features to directly approach this task, but these…

Language has always been one of humanity's defining characteristics. Visual Language Identification (VLI) is a relatively new field of research that is complex and largely understudied. In this paper, we present a preliminary study in which…

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…

We present several methods to improve the generalisation of language identification (LID) systems to new speakers and to new domains. These methods involve Spectral augmentation, where spectrograms are masked in the frequency or time bands…

Multilingual automatic speech recognition (ASR) models have shown great promise in recent years because of the simplified model training and deployment process. Conventional methods either train a universal multilingual model without taking…

While language identification is a fundamental speech and language processing task, for many languages and language families it remains a challenging task. For many low-resource and endangered languages this is in part due to resource…

Multilingual language models often perform unevenly across different languages due to limited generalization capabilities for some languages. This issue is significant because of the growing interest in making universal language models that…

Globalization and multiculturalism continue to produce increasingly diverse speech varieties. Yet current spoken dialogue systems frequently fail on under-represented dialects and accents, often misidentifying the input language and causing…

Target Language Extraction aims to extract speech in a specific language from a mixture waveform that contains multiple speakers speaking different languages. The human auditory system is adept at performing this task with the knowledge of…

In this paper, we extend previous self-supervised approaches for language identification by experimenting with Conformer based architecture in a multilingual pre-training paradigm. We find that pre-trained speech models optimally encode…

Due to the inherent difficulty in modeling phonetic similarities across different languages, code-switching speech recognition presents a formidable challenge. This study proposes a Collaborative-MoE, a Mixture of Experts (MoE) model that…

Building a multilingual Automated Speech Recognition (ASR) system in a linguistically diverse country like India can be a challenging task due to the differences in scripts and the limited availability of speech data. This problem can be…

Recent advancements in deep learning have significantly enhanced multilingual automatic speech recognition (ASR) due to the development of advanced model architectures and available large-scale multilingual datasets. Despite that,…

We introduce TitaNet-LID, a compact end-to-end neural network for Spoken Language Identification (LID) that is based on the ContextNet architecture. TitaNet-LID employs 1D depth-wise separable convolutions and Squeeze-and-Excitation layers…

Pure acoustic neural models, particularly the LSTM-RNN model, have shown great potential in language identification (LID). However, the phonetic information has been largely overlooked by most of existing neural LID models, although this…

We present a novel approach to multilingual audio-visual speech recognition tasks by introducing a single model on a multilingual dataset. Motivated by a human cognitive system where humans can intuitively distinguish different languages…

Most state-of-the-art spoken language identification models are closed-set; in other words, they can only output a language label from the set of classes they were trained on. Open-set spoken language identification systems, however, gain…

Google's multilingual speech recognition system combines low-level acoustic signals with language-specific recognizer signals to better predict the language of an utterance. This paper presents our experience with different signal…

The prevalence of the powerful multilingual models, such as Whisper, has significantly advanced the researches on speech recognition. However, these models often struggle with handling the code-switching setting, which is essential in…