Related papers: Contextualized Token Discrimination for Speech Sea…
We present Contextual Query Rewrite (CQR) a dataset for multi-domain task-oriented spoken dialogue systems that is an extension of the Stanford dialog corpus (Eric et al., 2017a). While previous approaches have addressed the issue of…
As more and more online search queries come from voice, automatic speech recognition becomes a key component to deliver relevant search results. Errors introduced by automatic speech recognition (ASR) lead to irrelevant search results…
Human listeners exhibit the remarkable ability to segregate a desired sound from complex acoustic scenes through selective auditory attention, motivating the study of Targeted Sound Detection (TSD). The task requires detecting and…
With the tremendous growth in the number of scientific papers being published, searching for references while writing a scientific paper is a time-consuming process. A technique that could add a reference citation at the appropriate place…
Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios.…
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…
Punctuated text prediction is crucial for automatic speech recognition as it enhances readability and impacts downstream natural language processing tasks. In streaming scenarios, the ability to predict punctuation in real-time is…
In the recent past, social media platforms have helped people in connecting and communicating to a wider audience. But this has also led to a drastic increase in cyberbullying. It is essential to detect and curb hate speech to keep the…
Recent dialogue systems rely on turn-based spoken interactions, requiring accurate Automatic Speech Recognition (ASR). Errors in ASR can significantly impact downstream dialogue tasks. To address this, using dialogue context from user and…
Air traffic management and specifically air-traffic control (ATC) rely mostly on voice communications between Air Traffic Controllers (ATCos) and pilots. In most cases, these voice communications follow a well-defined grammar that could be…
Grammatical error detection (GED) in non-native writing requires systems to identify a wide range of errors in text written by language learners. Error detection as a purely supervised task can be challenging, as GED datasets are limited in…
Automatic pronunciation error detection (APED) plays an important role in the domain of language learning. As for the previous ASR-based APED methods, the decoded results need to be aligned with the target text so that the errors can be…
With the increased applications of automatic speech recognition (ASR) in recent years, it is essential to automatically insert punctuation marks and remove disfluencies in transcripts, to improve the readability of the transcripts as well…
Recent advances in End-to-End (E2E) Spoken Language Understanding (SLU) have been primarily due to effective pretraining of speech representations. One such pretraining paradigm is the distillation of semantic knowledge from…
Unstructured clinical data can serve as a unique and rich source of information that can meaningfully inform clinical practice. Extracting the most pertinent context from such data is critical for exploiting its true potential toward…
Segmentation-based methods are widely used for scene text detection due to their superiority in describing arbitrary-shaped text instances. However, two major problems still exist: 1) current label generation techniques are mostly empirical…
Contextual spelling correction models are an alternative to shallow fusion to improve automatic speech recognition (ASR) quality given user vocabulary. To deal with large user vocabularies, most of these models include candidate retrieval…
Query-by-example search often uses dynamic time warping (DTW) for comparing queries and proposed matching segments. Recent work has shown that comparing speech segments by representing them as fixed-dimensional vectors --- acoustic word…
Contextual knowledge is important for real-world automatic speech recognition (ASR) applications. In this paper, a novel tree-constrained pointer generator (TCPGen) component is proposed that incorporates such knowledge as a list of biasing…
Synthesized speech is common today due to the prevalence of virtual assistants, easy-to-use tools for generating and modifying speech signals, and remote work practices. Synthesized speech can also be used for nefarious purposes, including…