5 papers
Hybrid Decoding: Rapid Pass and Selective Detailed Correction for Sequence Models
Yunkyu Lim, Jihwan Park, Hyung Yong Kim +2
Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large s…
Bridging the Gap between Audio and Text using Parallel-attention for User-defined Keyword Spotting
Youkyum Kim, Jaemin Jung, Jihwan Park +2
This paper proposes a novel user-defined keyword spotting framework that accurately detects audio keywords based on text enrollment. Since audio data possesses additional acoustic…
Joint unsupervised and supervised learning for context-aware language identification
Jinseok Park, Hyung Yong Kim, Jihwan Park +3
Language identification (LID) recognizes the language of a spoken utterance automatically. According to recent studies, LID models trained with an automatic speech recognition (ASR…
That's What I Said: Fully-Controllable Talking Face Generation
Youngjoon Jang, Kyeongha Rho, Jong-Bin Woo +5
The goal of this paper is to synthesise talking faces with controllable facial motions. To achieve this goal, we propose two key ideas. The first is to establish a canonical space…
Metric Learning for User-defined Keyword Spotting
Jaemin Jung, Youkyum Kim, Jihwan Park +4
The goal of this work is to detect new spoken terms defined by users. While most previous works address Keyword Spotting (KWS) as a closed-set classification problem, this limits t…