Speech Recognition System for Embedded Real-time Applications

被引：7
作者：
Cheng, Octavian [1 ]
Abdulla, Waleed [1 ]
Salcic, Zoran [1 ]
机构：
[1] Univ Auckland, Dept Elect & Comp Engn, Auckland 1, New Zealand
来源：
2009 IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY (ISSPIT 2009) | 2009年
关键词：
Speech recognition; Embedded application; Real-time system; Softcore processor; Field Programmable Gate Arrays;
D O I：
10.1109/ISSPIT.2009.5407487
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
In this paper a hardware/software co-processing speech recognizer for embedded applications is proposed. The system mainly consists of a softcore processor and a hardware accelerator The accelerator is responsible for GMM emission probability calculation, which is the major computational bottleneck. To alleviate the memory bandwidth issue, the hardware accelerator uses double-buffering, which allows parallel operation of data retrieval and GMM computation. The proposed accelerator is synthesized on an Altera Stratix II FPGA device together with a Nios II softcore processor running at 100MHz. The proposed system is compared with a pure software-based system using test utterances from the Resource Management (RM1) corpus. For a speech utterance length of 2.49s, the decoding time reduces from 6.64s to 2.48s. The real-time factor improves from 2.67 to 1.00. The word accuracy rate of the proposed system on the RM corpus is 93.42%.
引用
收藏
页码：118 / 122
页数：5
相关论文
共 50 条
  • [21] Compact hardware liquid state machines on FPGA for real-time speech recognition
    Schrauwen, Benjamin
    D'Haene, Michiel
    Verstraeten, David
    Van Campenhout, Jan
    NEURAL NETWORKS, 2008, 21 (2-3) : 511 - 523
  • [22] Augmenting the Social Presence of Interactive Characters Using Real-time Speech Recognition
    Yamano, Mizuki
    Song, Zhihao
    Hoshino, Junichi
    2022 NICOGRAPH INTERNATIONAL, NICOINT 2022, 2022, : 85 - 88
  • [23] EcoScript: A Real-Time Presentation Supporting Tool using a Speech Recognition Model
    Lee, Eunycoul
    Yang, Eunsco
    Huh, Jinyoung
    Oh, Uran
    2024 IEEE INTERNATIONAL CONFERENCE ON INFORMATION REUSE AND INTEGRATION FOR DATA SCIENCE, IRI 2024, 2024, : 96 - 101
  • [24] Real-Time Integration of Dynamic Context Information for Improving Automatic Speech Recognition
    Oualil, Youssef
    Schulder, Marc
    Helmke, Hartmut
    Schmidt, Anna
    Klakow, Dietrich
    16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 2107 - 2111
  • [25] A fifteen channels real time speech recognition board for computer telephony applications
    Gerard, C
    Ouahabi, A
    IMTC/97 - IEEE INSTRUMENTATION & MEASUREMENT TECHNOLOGY CONFERENCE: SENSING, PROCESSING, NETWORKING, PROCEEDINGS VOLS 1 AND 2, 1997, : 193 - 196
  • [26] Embedded speech recognition system for intelligent robot
    Hong, Qingyang
    Zhang, Caihong
    Chen, Xiaoyang
    Chen, Yan
    14TH INTERNATIONAL CONFERENCE ON MECHATRONICS AND MACHINE VISION IN PRACTICE 2007, PROCEEDINGS, 2007, : 35 - +
  • [27] Embedded Speech recognition interaction system research
    Luo, Qiong
    PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON INFORMATION SCIENCES, MACHINERY, MATERIALS AND ENERGY (ICISMME 2015), 2015, 126 : 1035 - 1038
  • [28] Real-Time Iris Recognition System Using A Proposed Method
    Wibowo, Eri Prasetyo
    Maulana, Wisnu Sukma
    PROCEEDINGS OF THE 2009 INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING SYSTEMS, 2009, : 98 - 102
  • [29] An Adaptive Embedded Multi-core Real-Time System Scheduling
    Lee, Liang-Teh
    Chang, Hung-Yuan
    Luk, Wai-Min
    UBIQUITOUS COMPUTING AND MULTIMEDIA APPLICATIONS, PT I, 2011, 150 : 263 - 272
  • [30] Reliability Evaluation of Embedded Real-time System based on Error Scenario
    Ran, Zheng
    Yan, Hua
    Li, Yun
    CURRENT TRENDS IN COMPUTER SCIENCE AND MECHANICAL AUTOMATION (CSMA), VOL 2, 2017, : 548 - 560
12345