20 citations · 93 across the 26 of their papers we have counts for
7 papers · 1 filter
On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition
Zhiping Zeng, Yerbolat Khassanov, Van Tung Pham +3
Code-switching (CS) refers to a linguistic phenomenon where a speaker uses different languages in an utterance or between alternating utterances. In this work, we study end-to-end…
Error Reduction Network for DBLSTM-based Voice Conversion
Mingyang Zhang, Berrak Sisman, Sai Sirisha Rallabandi +2
So far, many of the deep learning approaches for voice conversion produce good quality speech by using a large amount of training data. This paper presents a Deep Bidirectional Lon…
Generative x-vectors for text-independent speaker verification
Longting Xu, Rohan Kumar Das, Emre Yılmaz +2
Speaker verification (SV) systems using deep neural network embeddings, so-called the x-vector systems, are becoming popular due to its good performance superior to the i-vector sy…
Is Neuromorphic MNIST neuromorphic? Analyzing the discriminative power of neuromorphic datasets in the time domain
Laxmi R. Iyer, Yansong Chua, Haizhou Li
The advantage of spiking neural networks (SNNs) over their predecessors is their ability to spike, enabling them to use spike timing for coding and efficient computing. A neuromorp…
Learning Acoustic Word Embeddings with Temporal Context for Query-by-Example Speech Search
Yougen Yuan, Cheung-Chi Leung, Lei Xie +3
We propose to learn acoustic word embeddings with temporal context for query-by-example (QbE) speech search. The temporal context includes the leading and trailing word sequences o…
A Cost-Sensitive Deep Belief Network for Imbalanced Classification
Chong Zhang, Kay Chen Tan, Haizhou Li +1
Imbalanced data with a skewed class distribution are common in many real-world applications. Deep Belief Network (DBN) is a machine learning technique that is effective in classifi…