website update

_bibliography/papers.bib

@@ -17,6 +17,242 @@ @string{ICLR
 @string{NeurIPS = {Proceedings of the Conference on Neural Information Processing Systems}}
 
 
+
+@inproceedings{wu_icassp2024,
+    abbr={SE},
+    abbr_publisher={ICASSP},
+author={Shilong Wu and Chenxi Wang and Hang Chen and Yusheng Dai and Chenyue Zhang and Ruoyu Wang and Hongbo Lan and Jun Du and Chin-hui Lee and Jingdong Chen and Shinji Watanabe and Sabato Marco Siniscalchi and Odette Scharenborg and Zhong-Qiu Wang and Jia Pan and Jianqing Gao},
+title={The Multimodal Information Based Speech Processing (MISP) 2023 Challenge: Audio-Visual Target Speaker Extraction},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{yang_icassp2024,
+    abbr={Audio},
+    abbr_publisher={ICASSP},
+author={Muqiao Yang and Umberto Cappellazzo and Xiang Li and Shinji Watanabe and Bhiksha Raj},
+title={Improving Continual Learning of Acoustic Scene Classification via Mutual Information Optimization},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{tang_icassp2024,
+    abbr={ASR},
+    abbr_publisher={ICASSP},
+author={Jiyang Tang and Kwangyoun Kim and Suwon Shon and Felix Wu and Prashant Sridhar and Shinji Watanabe},
+title={Improving ASR Contextual Biasing with Guided Attention},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{jung_icassp2024,
+    abbr={SLU},
+    abbr_publisher={ICASSP},
+author={Jee-weon Jung and Roshan Sharma and William Chen and Bhiksha Raj and Shinji Watanabe},
+title={AugSumm: Towards Generalizable Speech Summarization Using Synthetic Labels from Large Language Models},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{maiti_icassp2024,
+    abbr={ASR&TTS},
+    abbr_publisher={ICASSP},
+author={Soumi Maiti and Yifan Peng and Shukjae Choi and Jee-weon Jung and Xuankai Chang and Shinji Watanabe},
+title={Voxtlm: Unified Decoder-Only Models for Consolidating Speech Recognition, Synthesis and Speech, Text Continuation Tasks},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{hussein1_icassp2024,
+    abbr={ASR},
+    abbr_publisher={ICASSP},
+author={Amir Hussein and Dorsa Zeinali and Ondřej Klejch and Matthew Wiesner and Brian Yan and Shammur Chowdhury and Ahmed Ali and Shinji Watanabe and Sanjeev Khudanpur},
+title={Speech Collage: Code-Switched Audio Generation by Collaging Monolingual Corpora},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{hussein2_icassp2024,
+    abbr={ST},
+    abbr_publisher={ICASSP},
+author={Amir Hussein and Brian Yan and Antonios Anastasopoulos and Shinji Watanabe and Sanjeev Khudanpur},
+title={Enhancing End-to-End Conversational Speech Translation Through Target Language Context Utilization},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{medina_icassp2024,
+    abbr={ASR},
+    abbr_publisher={ICASSP},
+author={Salvador Medina and Sarah Taylor and Carsten Stoll and Gareth Edwards and Alex Hauptmann and Shinji Watanabe and Iain Matthews},
+title={Phisanet: Phonetically Informed Speech Animation Network},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{cornell_icassp2024,
+    abbr={SD&ASR},
+    abbr_publisher={ICASSP},
+author={Samuele Cornell and Jee-weon Jung and Shinji Watanabe and Stefano Squartini},
+title={One Model to Rule Them All? Towards End-to-End Joint Speaker Diarization and Speech Recognition},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{huang_icassp2024,
+    abbr={ASR},
+    abbr_publisher={ICASSP},
+author={Ruizhe Huang and Xiaohui Zhang and Zhaoheng Ni and Li Sun and Moto Hira and Jeff Hwang and Vimal Manohar and Vineel Pratap and Shinji Watanabe and Daniel Povey and Sanjeev Khudanpur},
+title={Less Peaky and More Accurate CTC Forced Alignment by Pruned CTC Loss and Label Priors},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{maekaku_icassp2024,
+    abbr={SSL},
+    abbr_publisher={ICASSP},
+author={Takashi Maekaku and Jiatong Shi and Xuankai Chang and Yuya Fujita and Shinji Watanabe},
+title={HuberTopic: Enhancing Semantic Representation of Hubert Through Self-Supervision Utilizing Topic Model},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{chang_icassp2024,
+    abbr={ASR&ST&SLU},
+    abbr_publisher={ICASSP},
+author={Xuankai Chang and Brian Yan and Kwanghee Choi and Jee-weon Jung and Yichen Lu and Soumi Maiti and Roshan Sharma and Jiatong Shi and Jinchuan Tian and Shinji Watanabe and Yuya Fujita and Takashi Maekaku and Pengcheng Guo and Yao-Fei Cheng and Pavel Denisov and Kohei Saijo and Hsiu-Hsuan Wang},
+title={Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{huang_chienyu_icassp2024,
+    abbr={LLM&SLU},
+    abbr_publisher={ICASSP},
+author={Chien-yu Huang and Ke-Han Lu and Shih-Heng Wang and Chun-Yi Kuan and Chi-Yuan Hsiao and Haibin Wu and Siddhant Arora and Kai-Wei Chang and Jiatong Shi and Yifan Peng and Roshan Sharma and Shinji Watanabe and Bhiksha Ramakrishnan and Shady Shehata and Hung-yi Lee},
+title={Dynamic-Superb: Towards a Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{yan_brian_icassp2024,
+    abbr={ST},
+    abbr_publisher={ICASSP},
+author={Brian Yan and Xuankai Chang and Antonios Anastasopoulos and Yuya Fujita and Shinji Watanabe},
+title={Cross-Modal Multi-Tasking for Speech-to-Text Translation via Hard Parameter Sharing},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{arora_siddhant_icassp2024,
+    abbr={ASR},
+    abbr_publisher={ICASSP},
+author={Siddhant Arora and George Saon and Shinji Watanabe and Brian Kingsbury},
+title={Semi-Autoregressive Streaming ASR with Label Context},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{shon_icassp2024,
+    abbr={SSL},
+    abbr_publisher={ICASSP},
+author={Suwon Shon and Kwangyoun Kim and Prashant Sridhar and Yi-Te Hsu and Shinji Watanabe and Karen Livescu},
+title={Generative Context-Aware Fine-Tuning of Self-Supervised Speech Models},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{sudo_icassp2024,
+    abbr={ASR},
+    abbr_publisher={ICASSP},
+author={Yui Sudo and Shakeel Muhammad and Yosuke Fukumoto and Yifan Peng and Shinji Watanabe},
+title={Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Search},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{chen_william_icassp2024,
+    abbr={SSL},
+    abbr_publisher={ICASSP},
+author={William Chen and Takatomo Kano and Atsunori Ogawa and Marc Delcroix and Shinji Watanabe},
+title={Train Long and Test Long: Leveraging Full Document Contexts in Speech Processing},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{zhang_icassp2024,
+    abbr={SE},
+    abbr_publisher={ICASSP},
+author={Wangyou Zhang and Jee-weon Jung and Shinji Watanabe and Yanmin Qian},
+title={Improving Design of Input Condition Invariant Speech Enhancement},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{futami_icassp2024,
+    abbr={ASR},
+    abbr_publisher={ICASSP},
+author={Hayato Futami and Emiru Tsunoo and Yosuke Kashiwagi and Hiroaki Ogawa and Siddhant Arora and Shinji Watanabe},
+title={Phoneme-Aware Encoding for Prefix-Tree-Based Contextual ASR},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{lee_younglo_icassp2024,
+    abbr={SS},
+    abbr_publisher={ICASSP},
+author={Younglo Lee and Shukjae Choi and Byeong-Yeol Kim and Zhong-Qiu Wang and Shinji Watanabe},
+title={Boosting Unknown-Number Speaker Separation with Transformer Decoder-Based Attractor},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{yeo_icassp2024,
+    abbr={ASR},
+    abbr_publisher={ICASSP},
+author={Jeong Hun Yeo and Minsu Kim and Shinji Watanabe and Yong Man Ro},
+title={Visual Speech Recognition for Low-Resource Languages with Automatic Labels from Whisper Model},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{kim_minsu_icassp2024,
+    abbr={Caption},
+    abbr_publisher={ICASSP},
+author={Minsu Kim and Jeongsoo Choi and Soumi Maiti and Jeong Hun Yeo and Shinji Watanabe and Yong Man Ro},
+title={Towards Practical and Efficient Image-to-Speech Captioning with Vision-Language Pre-Training and Multi-Modal Tokens},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{choi_kwanghee_icassp2024,
+    abbr={SSL},
+    abbr_publisher={ICASSP},
+author={Kwanghee Choi and Jee-weon Jung and Shinji Watanabe},
+title={Understanding Probe Behaviors Through Variational Bounds of Mutual Information},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{wu_shihlun_icassp2024,
+    abbr={Caption},
+    abbr_publisher={ICASSP},
+author={Shih-Lun Wu and Xuankai Chang and Gordon Wichern and Jee-weon Jung and François Germain and Jonathan Le Roux and Shinji Watanabe},
+title={Improving Audio Captioning Models with Fine-Grained Audio Features, Text Embedding Supervision, and LLM Mix-Up Augmentation},
+booktitle=ICASSP,
+year={2024}
+}
+
+@inproceedings{tseng_icassp2024,
+    abbr={SSL},
+    abbr_publisher={ICASSP},
+author={Yuan Tseng and Layne Berry and Yi-Ting Chen and I-Hsiang Chiu and Hsuan-Hao Lin and Max Liu and Puyuan Peng and Yi-Jen Shih and Hung-Yu Wang and Haibin Wu and Po-Yao Huang and Chun-Mao Lai and Shang-Wen Li and David Harwath and Yu Tsao and Shinji Watanabe and Abdelrahman Mohamed and Chi Luen Feng and Hung-yi Lee},
+title={AV-Superb: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models},
+booktitle=ICASSP,
+year={2024}
+}
+
+
 @inproceedings{chou2023evaluating,
     abbr={ASR},
     abbr_publisher={ASRU},
@@ -1417,7 +1653,7 @@ @inproceedings{wu_apsipa2021
 @inproceedings{inaguma2021iwslt,
   abbr={ST},
   abbr_publisher={IWSLT},
-  title={{ESP}net-{ST} {IWSLT} 2021 Offline Speech Translation System},
+  title={ESPnet-ST IWSLT 2021 Offline Speech Translation System},
   author={Inaguma, Hirofumi and Yan, Brian and Dalmia, Siddharth and Guo, Pengcheng and Shi, Jiatong and Duh, Kevin and Watanabe, Shinji},
   booktitle=IWSLT,
   pages={100--109},

_includes/header.html

@@ -31,7 +31,15 @@
               {% endif %}
             </a>
           </li>
-
+          <!-- Blog -->
+          <li class="nav-item {% if page.url contains 'blog' %}active{% endif %}">
+            <a class="nav-link" href="{{ '/blog/' | relative_url }}">
+              Activities
+              {% if page.title == "blog" %}
+              <span class="sr-only">(current)</span>
+              {% endif %}
+            </a>
+          </li>
           <!-- Other pages -->
           {% assign sorted_pages = site.pages | sort: "order" %}
           {% for p in sorted_pages %}
@@ -47,15 +55,7 @@
           {% endif %}
           {% endfor %}
           {% if site.blog_name %}
-          <!-- Blog -->
-          <li class="nav-item {% if page.url contains 'blog' %}active{% endif %}">
-            <a class="nav-link" href="{{ '/blog/' | relative_url }}">
-              Activities
-              {% if page.title == "blog" %}
-              <span class="sr-only">(current)</span>
-              {% endif %}
-            </a>
-          </li>
+
           {% endif %}
           {% if site.enable_darkmode %}
             <div class = "toggle-container">

_pages/courses.md

@@ -4,7 +4,7 @@ permalink: /courses/
 title: Courses
 description: This page holds the courses related to our lab.
 nav: true
-order: 5
+order: 6
 ---
 
 ### 2023 Fall

_pages/info.md

@@ -3,7 +3,7 @@ layout: page
 permalink: /info/
 title: Info
 nav: true
-order: 7
+order: 8
 ---
 
 This page has some information guidelines for members of WAVLab.

_pages/members.md

@@ -175,6 +175,26 @@ order: 1
 </div>
 <hr />
 
+#### Visting Faculty
+<div class="row mt-3">
+    <div class="col-sm mt-3 mt-md-0">
+        <div class="square">
+        <a href="https://home.ttic.edu/~klivescu/" target="_blank" rel="noopener noreferrer">
+            <img class="img-fluid rounded z-depth-1" src="{{ site.baseurl }}/assets/img/12.jpg">
+        </a></div>
+        <div class="caption">
+            Karen Livescu
+        </div>
+    </div>
+    <div class="col-sm mt-3 mt-md-0">
+    </div>
+    <div class="col-sm mt-3 mt-md-0">
+    </div>
+    <div class="col-sm mt-3 mt-md-0">
+    </div>
+</div>
+<hr />
+
 #### Post-Doc
 <div class="row mt-3">
     <div class="col-sm mt-3 mt-md-1">

_pages/open-source.md

@@ -4,7 +4,7 @@ title: Open-source
 permalink: /open_source
 
 nav: true
-order: 4
+order: 5
 ---
 
 Our lab has been led and participated in the development of several open-source toolkits and datasets. The followings are some selected ones.

_pages/positions.md

@@ -3,7 +3,7 @@ layout: page
 permalink: /positions/
 title: Positions
 nav: true
-order: 8
+order: 9
 ---
 
 Thank you for considering working with us!

_pages/sphinx-lunch.md

@@ -3,7 +3,7 @@ layout: page
 permalink: /sphinx_lunch
 title: Sphinx Lunch
 nav: true
-order: 9
+order: 10
 ---
 
 Welcome to the Sphinx Speech Lunch at Carnegie Mellon University!

_pages/sponsors.md

@@ -4,7 +4,7 @@ permalink: /sponsors/
 title: Sponsors
 description: We appreciate the sponsorship from various partners. The list is sorted in alphabet order.
 nav: true
-order: 6
+order: 7
 ---