Related papers: Multi-Encoder-Decoder Transformer for Code-Switchi…

We present a decoder-only Conformer for automatic speech recognition (ASR) that processes speech and text in a single stack without external speech encoders or pretrained large language models (LLM). The model uses a modality-aware sparse…

The multi-decoder (MD) end-to-end speech translation model has demonstrated high translation quality by searching for better intermediate automatic speech recognition (ASR) decoder states as hidden intermediates (HI). It is a two-pass…

Sequence-to-sequence attention-based models have recently shown very promising results on automatic speech recognition (ASR) tasks, which integrate an acoustic, pronunciation and language model into a single neural network. In these models,…

This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by transfer learning from…

Multilingual speech recognition for both monolingual and code-switching speech is a challenging task. Recently, based on the Mixture of Experts (MoE), many works have made good progress in multilingual and code-switching ASR, but present…

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…

End-to-end modeling (E2E) of automatic speech recognition (ASR) blends all the components of a traditional speech recognition system into a unified model. Although it simplifies training and decoding pipelines, the unified model is hard to…

In multi-source sequence-to-sequence tasks, the attention mechanism can be modeled in several ways. This topic has been thoroughly studied on recurrent architectures. In this paper, we extend the previous work to the encoder-decoder…

Recognizing emotions from speech using machine learning has become an active research area due to its importance in building human-centered applications. However, while many studies have been conducted in English, German, and other European…

Code-switching, the interleaving of two or more languages within a sentence or discourse is pervasive in multilingual societies. Accurate language models for code-switched text are critical for NLP tasks. State-of-the-art data-intensive…

Code-switching, the alternation between two or more languages within communication, poses great challenges for Automatic Speech Recognition (ASR) systems. Existing models and datasets are limited in their ability to effectively handle these…

Code-Switching (CS) is a common phenomenon observed in several bilingual and multilingual communities, thereby attaining prevalence in digital and social media platforms. This increasing prominence demands the need to model CS languages for…

Machine transliteration is the process of automatically transforming the script of a word from a source language to a target language, while preserving pronunciation. Sequence to sequence learning has recently emerged as a new paradigm in…

Multilingual automatic speech recognition (ASR) in the medical domain serves as a foundational task for various downstream applications such as speech translation, spoken language understanding, and voice-activated assistants. This…

In this work, we use language modeling to investigate the factors that influence insertional code-switching. Code-switching occurs when a speaker alternates between one language variety (the primary language) and another (the secondary…

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural…

Multilingual end-to-end automatic speech recognition models are attractive due to its simplicity in training and deployment. Recent work on large-scale training of such models has shown promising results compared to monolingual models.…

In communication and storage systems, error correction codes (ECCs) are pivotal in ensuring data reliability. As deep learning's applicability has broadened across diverse domains, there is a growing research focus on neural network-based…

Speech applications dealing with conversations require not only recognizing the spoken words, but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate…

We focus on the problem of language modeling for code-switched language, in the context of automatic speech recognition (ASR). Language modeling for code-switched language is challenging for (at least) three reasons: (1) lack of available…