Search Results for author:
Found 15 papers, 3 papers with code
Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion Networks
In the realm of spoken language understanding (SLU), numerous natural language understanding (NLU) methodologies have been adapted by supplying large language models (LLMs) with transcribed speech instead of conventional written text.
Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue
Specifically, our framework serializes tasks in the order of current paralinguistic attribute prediction, response paralinguistic attribute prediction, and response text generation with autoregressive conditioning.
Discriminative Speech Recognition Rescoring with Pre-trained Language Models
In this study, we propose and explore several discriminative fine-tuning schemes for pre-trained LMs.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Personalization for BERT-based Discriminative Speech Recognition Rescoring
On a test set with personalized named entities, we show that each of these approaches improves word error rate by over 10%, against a neural rescoring baseline.
Scaling Laws for Discriminative Speech Recognition Rescoring Models
We study whether this scaling property is also applicable to second-pass rescoring, which is an important component of speech recognition systems.
Distillation Strategies for Discriminative Speech Recognition Rescoring
We also show that the proposed distillation can reduce the WER gap between the student and the teacher by 62% upto 100%.
Phone Duration Modeling for Speaker Age Estimation in Children
In this paper, we propose features specific to children and focus on speaker's phone duration as an important biomarker of children's age.
End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Study
A key desiderata for inclusive and accessible speech recognition technology is ensuring its robust performance to children's speech.
Confusion2vec 2.0: Enriching Ambiguous Spoken Language Representations with Subwords
Confusion2vec, motivated from human speech production and perception, is a word vector representation which encodes ambiguities present in human spoken language in addition to semantics and syntactic information.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
RNN based Incremental Online Spoken Language Understanding
We introduce and analyze different recurrent neural network architectures for incremental and online processing of the ASR transcripts and compare it to the existing offline systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+8
Behavior Gated Language Models
In this work we derive motivation from psycholinguistics and propose the addition of behavioral information into the context of language modeling.
Spoken Language Intent Detection using Confusion2Vec
In this paper, we address the spoken language intent detection under noisy conditions imposed by automatic speech recognition (ASR) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Confusion2Vec: Towards Enriching Vector Space Word Representations with Representational Ambiguities
In this paper, we propose a novel word vector representation, Confusion2Vec, motivated from the human speech production and perception that encodes representational ambiguity.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Transfer Learning from Adult to Children for Speech Recognition: Evaluation, Analysis and Recommendations
Evaluations are presented on (i) comparisons of earlier GMM-HMM and the newer DNN Models, (ii) effectiveness of standard adaptation techniques versus transfer learning, (iii) various adaptation configurations in tackling the variabilities present in children speech, in terms of (a) acoustic spectral variability, and (b) pronunciation variability and linguistic constraints.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Learning from Past Mistakes: Improving Automatic Speech Recognition Output via Noisy-Clean Phrase Context Modeling
In this work we model ASR as a phrase-based noisy transformation channel and propose an error correction system that can learn from the aggregate errors of all the independent modules constituting the ASR and attempt to invert those.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
