相关论文: Temporally Aligning Long Audio Interviews with Que…

Existing Indic ASR benchmarks often use scripted, clean speech and leaderboard driven evaluation that encourages dataset specific overfitting. In addition, strict single reference WER penalizes natural spelling variation in Indian…

Systems that can find correspondences between multiple modalities, such as between speech and images, have great potential to solve different recognition and data analysis tasks in an unsupervised manner. This work studies multimodal…

In recent years, user-generated audio content has proliferated across various media platforms, creating a growing need for efficient retrieval methods that allow users to search for audio clips using natural language queries. This task,…

Speech recognition models often obtain degraded performance when tested on speech with unseen accents. Domain-adversarial training (DAT) and multi-task learning (MTL) are two common approaches for building accent-robust ASR models. ASR…

Building Spoken Language Understanding (SLU) systems that do not rely on language specific Automatic Speech Recognition (ASR) is an important yet less explored problem in language processing. In this paper, we present a comparative study…

This work introduces \emph{cross-attention conformer}, an attention-based architecture for context modeling in speech enhancement. Given that the context information can often be sequential, and of different length as the audio that is to…

Audio-Visual Speech Recognition (AVSR) seeks to model, and thereby exploit, the dynamic relationship between a human voice and the corresponding mouth movements. A recently proposed multimodal fusion strategy, AV Align, based on…

We propose spoken sentence embeddings which capture both acoustic and linguistic content. While existing works operate at the character, phoneme, or word level, our method learns long-term dependencies by modeling speech at the sentence…

End-to-end automatic speech recognition (ASR) models, including both attention-based models and the recurrent neural network transducer (RNN-T), have shown superior performance compared to conventional systems. However, previous studies…

Selecting in-domain data from a large pool of diverse and out-of-domain data is a non-trivial problem. In most cases simply using all of the available data will lead to sub-optimal and in some cases even worse performance compared to…

Bootstrapping speech recognition on limited data resources has been an area of active research for long. The recent transition to all-neural models and end-to-end (E2E) training brought along particular challenges as these models are known…

End-to-end speech recognition is a promising technology for enabling compact automatic speech recognition (ASR) systems since it can unify the acoustic and language model into a single neural network. However, as a drawback, training of…

We propose data and knowledge-driven approaches for multilingual training of the automated speech recognition (ASR) system for a target language by pooling speech data from multiple source languages. Exploiting the acoustic similarities…

Despite Telugu being spoken by over 80 million people, speech translation research for this morphologically rich language remains severely underexplored. We address this gap by developing a high-quality Telugu--English speech translation…

Fine-tuning multilingual ASR models like Whisper for low-resource languages often improves read speech but degrades spontaneous audio performance, a phenomenon we term studio-bias. To diagnose this mismatch, we introduce Vividh-ASR, a…

The vast majority of ASR research uses corpora in which both the training and test data have been pre-segmented into utterances. In most real-word ASR use-cases, however, test audio is not segmented, leading to a mismatch between…

Recently, self-supervised pre-training has shown significant improvements in many areas of machine learning, including speech and NLP. We propose using large self-supervised pre-trained models for both audio and text modality with…

End-to-end (E2E) models have been explored for large speech corpora and have been found to match or outperform traditional pipeline-based systems in some languages. However, most prior work on end-to-end models use speech corpora exceeding…

We explore self-supervised models that can be potentially deployed on mobile devices to learn general purpose audio representations. Specifically, we propose methods that exploit the temporal context in the spectrogram domain. One method…

Audio-text retrieval (ATR), which retrieves a relevant caption given an audio clip (A2T) and vice versa (T2A), has recently attracted much research attention. Existing methods typically aggregate information from each modality into a single…