18 accepted papers
Automatic speech recognition (ASR) models with low-footprint are increasingly being deployed on edge devices for conversational agents, which enhances privacy. We study the problem of federated continual incremental learning for recurrent neural network-transducer (RNN-T) ASR models in the privacy-e…
Acoustic events have a hierarchical structure analogous to a tree (or a directed acyclic graph). In this work, we propose a structure-aware semi-supervised learning framework for acoustic event classification (AEC). Our hypothesis is that the audio label structure contains useful information that is…
Modern speaker verification models use deep neural networks to encode utterance audio into discriminative embedding vectors. During the training process, these networks are typically optimized to differentiate arbitrary speakers. This learning process biases the learning of fine voice characteristic…
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. SLU models, which either directly extract semantics from audio or are composed of pipelined automatic speech reco…
The study of keyword spotting, a subfield within the broader field of speech recognition that centers around identifying individual keywords in speech audio, has gained particular importance in recent years with the rise of personal voice assistants such as Alexa. As voice assistants aim to rapidly…
Conventional dynamic language switching enables seamless multilingual interactions by running several monolingual ASR systems in parallel and triggering the appropriate downstream components using a standalone language identification (LID) service. Since this solution is neither scalable nor cost- a…
Spoken language understanding (SLU) is the task of inferring the semantics of spoken utterances. Traditionally, this has been achieved with a cascading combination of Automatic Speech Recognition (ASR) and Natural Language Understanding (NLU) modules that are optimized separately, which can lead to…
Neural network-based speech separation has received a surge of interest in recent years. Previously proposed methods either are speaker independent or extract a target speaker's voice by using his or her voice snippet. In applications such as home devices or office meeting transcriptions, a possible…
Unsupervised single-channel overlapped speech recognition is one of the hardest problems in automatic speech recognition (ASR). The problems can be modularized into three sub-problems: frame-wise interpreting, sequence level speaker tracing and speech recognition. Nevertheless, previous acoustic mod…
We describe the latest version of Microsoft's conversational speech recognition system for the Switchboard and CallHome domains. The system adds a CNN-BLSTM acoustic model to the set of model architectures we combined previously, and includes character-based and dialog session aware LSTM language mo…
This paper advances the design of CTC-based all-neural (or end-to-end) speech recognizers. We propose a novel symbol inventory, and a novel iterated-CTC method in which a second system is used to transform a noisy initial output into a cleaner version. We present a number of stabilization and initia…
We describe Microsoft's conversational speech recognition system, in which we combine recent developments in neural-network-based acoustic and language modeling to advance the state of the art on the Switchboard recognition task. Inspired by machine learning ensemble techniques, the system uses a ra…
The CD-DNN-HMM system has became the state-of-art system for large vocabulary continuous speech recognition (LVCSR) tasks, in which deep neural networks (DNN) plays a key role. However, DNN training suffers from the vanishing gradient problem, limiting training of deep models. In this work, we addre…
Deep neural networks (DNN) are a powerful tool for many large vocabulary continuous speech recognition (LVCSR) tasks. Training a very deep network is a challenging problem and pre-training techniques are needed in order to achieve the best results. In this paper, we propose a new type of network arc…
The performance-intensive part of a large-vocabulary continuous speech-recognition system is the Viterbi computation that determines the sequence of words that are most likely to generate the acoustic-state scores extracted from an input utterance. This paper presents an efficient parallel algorithm…
Deep neural network models have been successfully applied to many tasks such as image labeling and speech recognition. Mini-batch stochastic gradient descent is the most prevalent method for training these models. A critical part of successfully applying this method is choosing appropriate initial v…
In this paper, we propose two approaches to improve deep neural network (DNN) acoustic models for speech recognition in reverberant environments. Both methods utilize auxiliary information in training the DNN but differ in the type of information and the manner in which it is used. The first method…
We propose the prediction-adaptation-correction RNN (PAC-RNN), in which a correction DNN estimates the state posterior probability based on both the current frame and the prediction made on the past frames by a prediction DNN. The result from the main DNN is fed back to the prediction DNN to make be…