In this work, we perform an empirical comparison among the CTC, RNN-Transducer, and
attention-based Seq2Seq models for end-to-end speech recognition. We show that, without …

In the context of automatic speech recognition and acoustic event detection, an adaptive
procedure named per-channel energy normalization (PCEN) has recently shown to …

Achieving high accuracy with end-to-end speech recognizers requires careful parameter
initialization prior to training. Otherwise, the networks may fail to find a good local optimum …

Prior work has shown that connectionist temporal classification (CTC)-based automatic
speech recognition systems perform well when using bidirectional long short-term memory …

Speech classifiers of paralinguistic traits traditionally learn from diverse hand-crafted low-
level features, by selecting the relevant information for the task at hand. We explore an …

Wake word (WW) spotting is challenging in far-field due to the complexities and variations in
acoustic conditions and the environmental interference in signal transmission. A suite of …

Knowledge distillation (KD) has been widely used to improve the performance of a simpler
student model by imitating the outputs or intermediate representations of a more complex …

Detecting bird calls in audio is an important task for automatic wildlife monitoring, as well as
in citizen science and audio library management. This paper presents front-end acoustic …