Search Results for author:
Found 32 papers, 1 papers with code
RescoreBERT: Discriminative Speech Recognition Rescoring with BERT
Specifically, training a bidirectional model like BERT on a discriminative objective such as minimum WER (MWER) has not been explored.
Automatic Speech Recognition
Natural Language Understanding
+1
Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understanding
Recent years have seen significant advances in end-to-end (E2E) spoken language understanding (SLU) systems, which directly predict intents and slots from spoken audio.
Natural Language Understanding
Spoken Language Understanding
+1
Context-Aware Transformer Transducer for Speech Recognition
We also leverage both BLSTM and pretrained BERT based models to encode contextual data and guide the network training.
FANS: Fusing ASR and NLU for on-device SLU
In this paper, we introduce FANS, a new end-to-end SLU model that fuses an ASR audio encoder to a multi-task NLU decoder to infer the intent, slot tags, and slot values directly from a given input audio, obviating the need for transcription.
Bifocal Neural ASR: Exploiting Keyword Spotting for Inference Optimization
We present Bifocal RNN-T, a new variant of the Recurrent Neural Network Transducer (RNN-T) architecture designed for improved inference time latency on speech recognition tasks.
Amortized Neural Networks for Low-Latency Speech Recognition
We apply AmNets to the Recurrent Neural Network Transducer (RNN-T) to reduce compute cost and latency for an automatic speech recognition (ASR) task.
Learning a Neural Diff for Speech Models
As more speech processing applications execute locally on edge devices, a set of resource constraints must be considered.
End-to-End Spoken Language Understanding using RNN-Transducer ASR
We propose an end-to-end trained spoken language understanding (SLU) system that extracts transcripts, intents and slots from an input speech utterance.
Automatic Speech Recognition
Natural Language Understanding
+1
Do You Listen with One or Two Microphones? A Unified ASR Model for Single and Multi-Channel Audio
An ASR model that operates on both primary and auxiliary data can achieve better accuracy compared to a primary-only solution; and a model that can serve both primary-only (PO) and primary-plus-auxiliary (PPA) modes is highly desirable.
Attention-based Contextual Language Model Adaptation for Speech Recognition
When applied to a large de-identified dataset of utterances collected by a popular voice assistant platform, our method reduces perplexity by 7. 0% relative over a standard LM that does not incorporate contextual information.
Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End
On the other hand, a streaming system using per-frame intent posteriors as extra inputs for the RNN-T ASR system yields a 3. 33% relative WERR.
Wav2vec-C: A Self-supervised Model for Speech Representation Learning
However, the quantization process is regularized by an additional consistency network that learns to reconstruct the input features to the wav2vec 2. 0 network from the quantized representations in a way similar to a VQ-VAE model.
Personalization Strategies for End-to-End Speech Recognition Systems
We also describe a novel second-pass de-biasing approach: used in conjunction with a first-pass shallow fusion that optimizes on oracle WER, we can achieve an additional 14% improvement on personalized content recognition, and even improve accuracy for the general use case by up to 2. 5%.
Do as I mean, not as I say: Sequence Loss Training for Spoken Language Understanding
Spoken language understanding (SLU) systems extract transcriptions, as well as semantics of intent or named entities from speech, and are essential components of voice activated systems.
Automatic Speech Recognition
Natural Language Understanding
+1
Sparsification via Compressed Sensing for Automatic Speech Recognition
In the literature, such methods are referred to as sparse pruning.
Domain-aware Neural Language Models for Speech Recognition
As voice assistants become more ubiquitous, they are increasingly expected to support and perform well on a wide variety of use-cases across different domains.
REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling
Accents mismatching is a critical problem for end-to-end ASR.
Improving accuracy of rare words for RNN-Transducer through unigram shallow fusion
We show that this simple method can improve performance on rare words by 3. 7% WER relative without degradation on general test set, and the improvement from USF is additive to any additional language model based rescoring.
Speech To Semantics: Improve ASR and NLU Jointly via All-Neural Interfaces
Finally, we contrast these methods to a jointly trained end-to-end joint SLU model, consisting of ASR and NLU subsystems which are connected by a neural network based interface instead of text, that produces transcripts as well as NLU interpretation.
Automatic Speech Recognition
Natural Language Understanding
+1
Neural Composition: Learning to Generate from Multiple Models
Decomposing models into multiple components is critically important in many applications such as language modeling (LM) as it enables adapting individual components separately and biasing of some components to the user's personal preferences.
Streaming End-to-End Bilingual ASR Systems with Joint Language Identification
Experiments show that for English-Spanish, the bilingual joint ASR-LID architecture matches monolingual ASR and acoustic-only LID accuracies.
Neural Machine Translation for Multilingual Grapheme-to-Phoneme Conversion
Grapheme-to-phoneme (G2P) models are a key component in Automatic Speech Recognition (ASR) systems, such as the ASR system in Alexa, as they are used to generate pronunciations for out-of-vocabulary words that do not exist in the pronunciation lexicons (mappings like "e c h o" to "E k oU").
Streaming Language Identification using Combination of Acoustic Representations and ASR Hypotheses
A common approach to solve multilingual speech recognition is to run multiple monolingual ASR systems in parallel and rely on a language identification (LID) component that detects the input language.
Audio-attention discriminative language model for ASR rescoring
In this work, we propose to combine the benefits of end-to-end approaches with a conventional system using an attention-based discriminative language model that learns to rescore the output of a first-pass ASR system.
Scalable Multi Corpora Neural Language Models for ASR
Neural language models (NLM) have been shown to outperform conventional n-gram language models by a substantial margin in Automatic Speech Recognition (ASR) and other tasks.
Scalable language model adaptation for spoken dialogue systems
New application intents and interaction types are released for these systems over time, imposing challenges to adapt the LMs since the existing training data is no longer sufficient to model the future user interactions.
LSTM-based Whisper Detection
We prove that, with enough data, the LSTM model is indeed as capable of learning whisper characteristics from LFBE features alone compared to a simpler MLP model that uses both LFBE and features engineered for separating whisper and normal speech.
Device-directed Utterance Detection
In this work, we propose a classifier for distinguishing device-directed queries from background speech in the context of interactions with voice assistants.
Contextual Language Model Adaptation for Conversational Agents
Statistical language models (LM) play a key role in Automatic Speech Recognition (ASR) systems used by conversational agents.
Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding
This paper presents the design of the machine learning architecture that underlies the Alexa Skills Kit (ASK) a large scale Spoken Language Understanding (SLU) Software Development Kit (SDK) that enables developers to extend the capabilities of Amazon's virtual assistant, Alexa.
