Related papers: asr_eval: Algorithms and tools for multi-reference…

This study proposes a text classification algorithm based on large language models, aiming to address the limitations of traditional methods in capturing long-range dependencies, understanding contextual semantics, and handling class…

This paper presents recent progress on integrating speech separation and enhancement (SSE) into the ESPnet toolkit. Compared with the previous ESPnet-SE work, numerous features have been added, including recent state-of-the-art speech…

The ongoing research scenario for automatic speech recognition (ASR) envisions a clear division between end-to-end approaches and classic modular systems. Even though a high-level comparison between the two approaches in terms of their…

Large scale recommender models find most relevant items from huge catalogs, and they play a critical role in modern search and recommendation systems. To model the input space with large-vocab categorical features, a typical recommender…

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. Such embeddings can form the basis for speech search, indexing and discovery systems when conventional speech recognition is not possible. In…

As an important component of multimedia analysis tasks, audio classification aims to discriminate between different audio signal types and has received intensive attention due to its wide applications. Generally speaking, the raw signal can…

Automatic speech recognition (ASR) systems often degrade on accented speech because acoustic-phonetic and prosodic shifts induce a mismatch to training data, making labeled accent adaptation costly. However, common pseudo-label selection…

Code-switching (CS) refers to the switching of languages within a speech signal and results in language confusion for automatic speech recognition (ASR). To address language confusion, we propose a language alignment loss (LAL) that aligns…

Automatic speech recognition (ASR) is widely used in consumer electronics. ASR greatly improves the utility and accessibility of technology, but usually the output is only word sequences without punctuation. This can result in ambiguity in…

Large language models (LLMs) are being increasingly tuned to power complex generation tasks such as writing, fact-seeking, querying and reasoning. Traditionally, human or model feedback for evaluating and further tuning LLM performance has…

We propose a first step toward multilingual end-to-end automatic speech recognition (ASR) by integrating knowledge about speech articulators. The key idea is to leverage a rich set of fundamental units that can be defined "universally"…

Speech-to-Speech and Speech-to-Text translation are currently dynamic areas of research. In our commitment to advance these fields, we present SpeechAlign, a framework designed to evaluate the underexplored field of source-target alignment…

In streaming settings, speech recognition models have to map sub-sequences of speech to text before the full audio stream becomes available. However, since alignment information between speech and text is rarely available during training,…

In this paper, we propose a speaker verification method by an Attentive Multi-scale Convolutional Recurrent Network (AMCRN). The proposed AMCRN can acquire both local spatial information and global sequential information from the input…

Automatic Speech Recognition (ASR) transcripts often contain disfluencies, such as fillers, repetitions, and false starts, which reduce readability and hinder downstream applications like chatbots and voice assistants. If left unaddressed,…

Well-trained machine-learning models, which leverage large amounts of open-source software data, have now become an interesting approach to automating many software engineering tasks. Several SE tasks have all been subject to this approach,…

Self-supervised learning (SSL) approaches such as wav2vec 2.0 and HuBERT models have shown promising results in various downstream tasks in the speech community. In particular, speech representations learned by SSL models have been shown to…

Automatic Speech Recognition (ASR) performance for low-resource languages is still far behind that of higher-resource languages such as English, due to a lack of sufficient labeled data. State-of-the-art methods deploy self-supervised…

We develop two complementary advances for training no-reference (NR) speech quality estimators with independent datasets. Multi-dataset finetuning (MDF) pretrains an NR estimator on a single dataset and then finetunes it on multiple…

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…