This paper presents a brief survey on Automatic Speech Recognition and discusses the
major themes and advances made in the past 60 years of research, so as to provide a …

This paper presents the main paradigms for speaker identification, and recent work on
missing data methods to increase robustness. The feature extraction, speaker modeling and …

This paper investigates the problem of speaker identification and verification in noisy
conditions, assuming that speech signals are corrupted by environmental noise, but …

This paper examines how people communicate with computers using speech. Automatic
speech recognition (ASR) transforms speech into text, while automatic speech synthesis [or …

The popular frequency-domain features Mel-frequency cepstral coefficients (MFCCs) have
been widely used for the task of acoustic scene classification (ASC). The MFCC feature …

This paper describes a system that gives a mobile robot the ability to perform automatic
speech recognition with simultaneous speakers. A microphone array is used along with a …

Temporal dynamics and speaker characteristics are two important features of speech that
distinguish speech from noise. In this paper, we propose a method to maximally extract …

Autoregressive neural vocoders have achieved outstanding performance in speech
synthesis tasks such as text-to-speech and voice conversion. An autoregressive vocoder …

This paper investigates the effect of modeling subband correlation for noisy speech
recognition. Subband feature streams are assumed to be independent in many subband …

This paper considers the separation and recognition of overlapped speech sentences
assuming single-channel observation. A system based on a combination of several different …