Related papers: Linguistic-Acoustic Similarity Based Accent Shift …

Automatic Lyrics Transcription (ALT) aims to recognize lyrics from singing voices, similar to Automatic Speech Recognition (ASR) for spoken language, but faces added complexity due to domain-specific properties of the singing voice. While…

In this paper, we present Adaptive Computation Steps (ACS) algo-rithm, which enables end-to-end speech recognition models to dy-namically decide how many frames should be processed to predict a linguistic output. The model that applies ACS…

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,…

Simultaneous speech translation (SST) produces target text incrementally from partial speech input. Recent speech large language models (Speech LLMs) have substantially improved SST quality, yet they still struggle to correctly translate…

Context compression is an advanced technique that accelerates large language model (LLM) inference by converting long inputs into compact representations. Existing methods primarily rely on autoencoding tasks to train special compression…

We propose a novel approach for ASR N-best hypothesis rescoring with graph-based label propagation by leveraging cross-utterance acoustic similarity. In contrast to conventional neural language model (LM) based ASR rescoring/reranking…

Large Language Models (LLMs) have showcased exceptional performance across diverse NLP tasks, and their integration with speech encoder is rapidly emerging as a dominant trend in the Automatic Speech Recognition (ASR) field. Previous works…

We present Multiscale Audio Spectrogram Transformer (MAST) for audio classification, which brings the concept of multiscale feature hierarchies to the Audio Spectrogram Transformer (AST). Given an input audio spectrogram, we first patchify…

Cross-lingual speech emotion recognition (SER) is important for a wide range of everyday applications. While recent SER research relies heavily on large pretrained models for emotion training, existing studies often concentrate solely on…

Contextual biasing improves automatic speech recognition (ASR) by integrating external knowledge, such as user-specific phrases or entities, during decoding. In this work, we use an attention-based biasing decoder to produce scores for…

LLM-based automatic speech recognition models demonstrate strong performance by connecting audio encoders and LLMs. However, data scarcity of paired speech and transcription often hinders their adaptation to new domains, making text-only…

Existing research suggests that automatic speech recognition (ASR) models can benefit from additional contexts (e.g., contact lists, user specified vocabulary). Rare words and named entities can be better recognized with contexts. In this…

Thanks to the rise of self-supervised learning, automatic speech recognition (ASR) systems now achieve near-human performance on a wide variety of datasets. However, they still lack generalization capability and are not robust to domain…

Speech representations learned in a self-supervised fashion from massive unlabeled speech corpora have been adapted successfully toward several downstream tasks. However, such representations may be skewed toward canonical data…

Vision transformers (ViT) have made substantial progress for classification tasks in computer vision. Recently, Gong et. al. '21, introduced attention-based modeling for several audio tasks. However, relatively unexplored is the use of a…

Test-Time Adaptation (TTA) has emerged as a crucial solution to the domain shift challenge, wherein the target environment diverges from the original training environment. A prime exemplification is TTA for Automatic Speech Recognition…

An important and difficult task in code-switched speech recognition is to recognize the language, as lots of words in two languages can sound similar, especially in some accents. We focus on improving performance of end-to-end Automatic…

In this paper we propose a novel data augmentation method for attention-based end-to-end automatic speech recognition (E2E-ASR), utilizing a large amount of text which is not paired with speech signals. Inspired by the back-translation…

Automatic Speech Scoring (ASS) is the computer-assisted evaluation of a candidate's speaking proficiency in a language. ASS systems face many challenges like open grammar, variable pronunciations, and unstructured or semi-structured…

Building inclusive speech recognition systems is a crucial step towards developing technologies that speakers of all language varieties can use. Therefore, ASR systems must work for everybody independently of the way they speak. To…