Context-aware RNNLM Rescoring for Conversational Speech Recognition

被引:1
|
作者
Wei, Kun [1 ]
Guo, Pengcheng [1 ]
Lv, Hang [1 ]
Tu, Zhen [2 ]
Xie, Lei [1 ]
机构
[1] Northwestern Polytech Univ, Sch Comp Sci, Audio Speech & Language Proc Grp ASLP NPU, Xian, Peoples R China
[2] Zhuiyi Technol, Shenzhen, Peoples R China
关键词
conversational speech recognition; recurrent neural network language model; lattice-rescoring; LANGUAGE MODEL ADAPTATION;
D O I
10.1109/ISCSLP49672.2021.9362109
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Conversational speech recognition is regarded as a challenging task due to its free-style speaking and long-term contextual dependencies. Prior work has explored the modeling of long-range context through RNNLM rescoring with improved performance. To further take advantage of the persisted nature during a conversation, such as topics or speaker turn, we extend the rescoring procedure to a new context-aware manner. For RNNLM training, we capture the contextual dependencies by concatenating adjacent sentences with various tag words, such as speaker or intention information. For lattice rescoring, the lattice of adjacent sentences are also connected with the first-pass decoded result by tag words. Besides, we also adopt a selective concatenation strategy based on tf-idf, making the best use of contextual similarity to improve transcription performance. Results on four different conversation test sets show that our approach yields up to 13.1% and 6% relative char-error-rate (CER) reduction compared with 1st-pass decoding and common lattice-rescoring, respectively.
引用
收藏
页数:5
相关论文
共 50 条
  • [1] Controllable Context-aware Conversational Speech Synthesis
    Cong, Jian
    Yang, Shan
    Hu, Na
    Li, Guangzhi
    Xie, Lei
    Su, Dan
    [J]. INTERSPEECH 2021, 2021, : 4658 - 4662
  • [2] A PRUNED RNNLM LATTICE-RESCORING ALGORITHM FOR AUTOMATIC SPEECH RECOGNITION
    Xu, Hainan
    Chen, Tongfei
    Gao, Dongji
    Wang, Yiming
    Li, Ke
    Goel, Nagendra
    Carmiel, Yishay
    Povey, Daniel
    Khudanpur, Sanjeev
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 5929 - 5933
  • [3] Towards Contrastive Context-Aware Conversational Emotion Recognition
    Zhang, Hanqing
    Song, Dawei
    [J]. IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2022, 13 (04) : 1879 - 1891
  • [4] VISUAL FEATURES FOR CONTEXT-AWARE SPEECH RECOGNITION
    Gupta, Abhinav
    Miao, Yajie
    Neves, Leonardo
    Metze, Florian
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 5020 - 5024
  • [5] CONTEXT-AWARE TRANSFORMER TRANSDUCER FOR SPEECH RECOGNITION
    Chang, Feng-Ju
    Liu, Jing
    Radfar, Martin
    Mouchtaris, Athanasios
    Omologo, Maurizio
    Rastrow, Ariya
    Kunzmann, Siegfried
    [J]. 2021 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU), 2021, : 503 - 510
  • [6] CONTEXT-AWARE ATTENTION MECHANISM FOR SPEECH EMOTION RECOGNITION
    Ramet, Gaetan
    Garner, Philip N.
    Baeriswyl, Michael
    Lazaridis, Alexandros
    [J]. 2018 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2018), 2018, : 126 - 131
  • [7] Context-Aware Conversational Developer Assistants
    Bradley, Nick C.
    Fritz, Thomas
    Holmes, Reid
    [J]. PROCEEDINGS 2018 IEEE/ACM 40TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE), 2018, : 993 - 1003
  • [8] An Architecture for the Design of Context-Aware Conversational Agents
    Griol, David
    Sanchez-Pi, Nayat
    Carbo, Javier
    Molina, Jose M.
    [J]. ADVANCES IN PRACTICAL APPLICATIONS OF AGENTS AND MULTIAGENT SYSTEMS, 2010, 70 : 41 - 46
  • [9] A Context-Aware Conversational Agent in the Rehabilitation Domain
    Mavropoulos, Thanassis
    Meditskos, Georgios
    Symeonidis, Spyridon
    Kamateri, Eleni
    Rousi, Maria
    Tzimikas, Dimitris
    Papageorgiou, Lefteris
    Eleftheriadis, Christos
    Adamopoulos, George
    Vrochidis, Stefanos
    Kompatsiaris, Ioannis
    [J]. FUTURE INTERNET, 2019, 11 (11):
  • [10] CONTEXT-AWARE NEURAL CONFIDENCE ESTIMATION FOR RARE WORD SPEECH RECOGNITION
    Qiu, David
    Munkhdalai, Tsendsuren
    He, Yanzhang
    Sim, Khe Chai
    [J]. 2022 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP, SLT, 2022, : 31 - 37