Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech
In this paper, we introduce a novel language identification system based on conformer layers. We propose an attentive temporal pooling mechanism to allow the model to carry information in long-form audio via a recurrent form, such that the inference can be performed in a streaming fashion. Additionally, we investigate two domain adaptation approaches to allow adapting an existing language identification model without retraining the model parameters for a new domain. We perform a comparative study of different model topologies under different constraints of model size, and find that conformer-based models significantly outperform LSTM and transformer based models. Our experiments also show that attentive temporal pooling and domain adaptation improve model accuracy.
Code (1)
Tasks
Domain AdaptationFormLanguage IdentificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Query-by-Example Keyword Spotting Using Spectral-Temporal Graph Attentive Pooling and Multi-Task Learning
Existing keyword spotting (KWS) systems primarily rely on predefined keyword phrases. However, the ability to recognize customized keywords is crucial for tailoring interactions with intelligent devices. In this paper, w…
Keyword SpottingMulti-Task LearningSC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR
In this work, we propose a Switch-Conformer-based MoE system named SC-MoE for unified streaming and non-streaming code-switching (CS) automatic speech recognition (ASR), where we design a streaming MoE layer consisting o…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Computational EfficiencyDecoder+4Nextformer: A ConvNeXt Augmented Conformer For End-To-End Speech Recognition
Conformer models have achieved state-of-the-art(SOTA) results in end-to-end speech recognition. However Conformer mainly focuses on temporal modeling while pays less attention on time-frequency property of speech feature…
speech-recognitionSpeech RecognitionTemporal-attentive Covariance Pooling Networks for Video Recognition
For video recognition task, a global representation summarizing the whole contents of the video snippets plays an important role for the final performance. However, existing video architectures usually generate it by usi…
Video RecognitionDCTX-Conformer: Dynamic context carry-over for low latency unified streaming and non-streaming Conformer ASR
Conformer-based end-to-end models have become ubiquitous these days and are commonly used in both streaming and non-streaming automatic speech recognition (ASR). Techniques like dual-mode and dynamic chunk training helpe…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition