Update documentation

Author: mdhk

_sources/index.md

@@ -5,7 +5,7 @@
 Pre-trained foundation models have revolutionized speech technology like many other adjacent fields. The combination of their capability and opacity has sparked interest in researchers trying to interpret the models in various ways. While interpretability in fields such as computer vision and natural language processing has made significant progress towards understanding model internals and explaining their decisions, speech technology has lagged behind despite the widespread use of complex, black-box neural models. Recent studies have begun to address this gap, marked by a growing body of literature focused on interpretability in the speech domain. This tutorial provides a structured overview of interpretability techniques, their applications, implications, and limitations when applied to speech models, aiming to help researchers and practitioners better understand, evaluate, debug, and optimize speech models while building trust in their predictions. In hands-on sessions, participants will explore how speech models encode distinct features (e.g., linguistic information) and utilize them in their inference. By the end, attendees will be equipped with the tools and knowledge to start analyzing and interpreting speech models in their own research, potentially inspiring new directions.
 
 ```{note} 
-We will present our tutorial about _Interpretability Techniques for Speech Models_ on **Sunday, August 17th** at this year's Interspeech conference in Rotterdam. <br> Check out the [programme](#interspeech-programme) below, and browse the materials through the sidebar menu.
+We presented our tutorial about _Interpretability Techniques for Speech Models_ on **Sunday, August 17th** at this year's Interspeech conference in Rotterdam. <br> Check out the [programme](#interspeech-programme) below, and browse the materials through the sidebar menu (an overview of all slides and notebooks is [here](https://interpretingdl.github.io/speech-interpretability-tutorial/interspeech2025/intro.html)).
 ```
 
 ![tutorial-overview-diagram](images/tutorial-overview.png)

_sources/interspeech2025/intro.md

@@ -1,11 +1,23 @@
 # Interspeech 2025 tutorial
 
+## Slides
+
+- [Grzegorz Chrupała - Introduction](https://raw.githubusercontent.com/interpretingdl/speech-interpretability-tutorial/refs/heads/main/book/interspeech2025/Interspeech2025_InterpretabilityTutorial_GrzegorzChrupa%C5%82a_Introduction.pdf)
+- [Martijn Bentum - Representational Analysis techniques](https://raw.githubusercontent.com/interpretingdl/speech-interpretability-tutorial/refs/heads/main/book/interspeech2025/Interspeech2025_InterpretabilityTutorial_MartijnBentum_RepresentationalAnalyses.pdf)
+- [Hosein Mohebbi - Context Mixing techniques](https://raw.githubusercontent.com/interpretingdl/speech-interpretability-tutorial/refs/heads/main/book/interspeech2025/Interspeech2025_InterpretabilityTutorial_HoseinMohebbi_ContextMixing.pdf)
+- [Gaofei Shen - Feature Attribution techniques](https://raw.githubusercontent.com/interpretingdl/speech-interpretability-tutorial/refs/heads/main/book/interspeech2025/Interspeech2025_InterpretabilityTutorial_GaofeiShen_FeatureAttribution.pdf)
+- [Marianne de Heer Kloots - Key takeaways & Future outlook](https://raw.githubusercontent.com/interpretingdl/speech-interpretability-tutorial/refs/heads/main/book/interspeech2025/Interspeech2025_InterpretabilityTutorial_MarianneDeHeerKloots_FutureOutlook.pdf)
+- [Willem Zuidema - Discussion](https://raw.githubusercontent.com/interpretingdl/speech-interpretability-tutorial/refs/heads/main/book/interspeech2025/Interspeech2025_InterpretabilityTutorial_WillemZuidema_Discussion.pdf)
+
+
+## Notebooks
+
 We provide four notebooks, exemplifying the interpretability techniques we cover in the tutorial. The notebooks are designed to work on Google Colab, open them through the links below:
 
-## Part I: Representation Understanding
+### Part I: Representation Understanding
 - [Probing exercise: Does Wav2Vec2 encode vocal tract movements?](https://colab.research.google.com/github/interpretingdl/speech-interpretability-tutorial/blob/main/book/interspeech2025/representational-analyses/probing.ipynb)
 - [Representation space comparisons: Locating acoustic and articulatory information in Wav2Vec2 with CKA](https://colab.research.google.com/github/interpretingdl/speech-interpretability-tutorial/blob/main/book/interspeech2025/representational-analyses/representation_space_comparisons.ipynb)
 
-## Part II: Feature Importance Scoring
+### Part II: Feature Importance Scoring
 - [Context Mixing: Quantifying Context-Mixing in Speech Transformers](https://colab.research.google.com/github/interpretingdl/speech-interpretability-tutorial/blob/main/book/interspeech2025/feature-importance-scoring/context_mixing.ipynb)
 - [Feature attribution: Explaining Speech Classification Models with Feature Attribution](https://colab.research.google.com/github/interpretingdl/speech-interpretability-tutorial/blob/main/book/interspeech2025/feature-importance-scoring/feature_attribution.ipynb)

index.html

@@ -410,10 +410,13 @@ <h1>Interpretability Techniques for Speech Models<a class="headerlink"
                   inspiring new directions.</p>
                 <div class="admonition note">
                   <p class="admonition-title">Note</p>
-                  <p>We will present our tutorial about <em>Interpretability Techniques for Speech Models</em> on
+                  <p>We presented our tutorial about <em>Interpretability Techniques for Speech Models</em> on
                     <strong>Sunday, August 17th</strong> at this year’s Interspeech conference in Rotterdam. <br> Check
                     out the <a class="reference internal" href="#interspeech-programme">programme</a> below, and browse
-                    the materials through the sidebar menu.</p>
+                    the materials through the sidebar menu (an overview of all slides and notebooks is <a
+                      class="reference external"
+                      href="https://interpretingdl.github.io/speech-interpretability-tutorial/interspeech2025/intro.html">here</a>).
+                  </p>
                 </div>
                 <p><img alt="tutorial-overview-diagram" src="_images/tutorial-overview.png" /></p>
                 <section id="programme-at-interspeech-2025">

interspeech2025/intro.html

@@ -356,8 +356,12 @@ <h2> Contents </h2>
             </div>
             <nav aria-label="Page">
                 <ul class="visible nav section-nav flex-column">
-<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#part-i-representation-understanding">Part I: Representation Understanding</a></li>
-<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#part-ii-feature-importance-scoring">Part II: Feature Importance Scoring</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#slides">Slides</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#notebooks">Notebooks</a><ul class="nav section-nav flex-column">
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#part-i-representation-understanding">Part I: Representation Understanding</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#part-ii-feature-importance-scoring">Part II: Feature Importance Scoring</a></li>
+</ul>
+</li>
 </ul>
             </nav>
         </div>
@@ -371,21 +375,35 @@ <h2> Contents </h2>
 
   <section class="tex2jax_ignore mathjax_ignore" id="interspeech-2025-tutorial">
 <h1>Interspeech 2025 tutorial<a class="headerlink" href="#interspeech-2025-tutorial" title="Link to this heading">#</a></h1>
+<section id="slides">
+<h2>Slides<a class="headerlink" href="#slides" title="Link to this heading">#</a></h2>
+<ul class="simple">
+<li><p><a class="reference external" href="https://raw.githubusercontent.com/interpretingdl/speech-interpretability-tutorial/refs/heads/main/book/interspeech2025/Interspeech2025_InterpretabilityTutorial_GrzegorzChrupa%C5%82a_Introduction.pdf">Grzegorz Chrupała - Introduction</a></p></li>
+<li><p><a class="reference external" href="https://raw.githubusercontent.com/interpretingdl/speech-interpretability-tutorial/refs/heads/main/book/interspeech2025/Interspeech2025_InterpretabilityTutorial_MartijnBentum_RepresentationalAnalyses.pdf">Martijn Bentum - Representational Analysis techniques</a></p></li>
+<li><p><a class="reference external" href="https://raw.githubusercontent.com/interpretingdl/speech-interpretability-tutorial/refs/heads/main/book/interspeech2025/Interspeech2025_InterpretabilityTutorial_HoseinMohebbi_ContextMixing.pdf">Hosein Mohebbi - Context Mixing techniques</a></p></li>
+<li><p><a class="reference external" href="https://raw.githubusercontent.com/interpretingdl/speech-interpretability-tutorial/refs/heads/main/book/interspeech2025/Interspeech2025_InterpretabilityTutorial_GaofeiShen_FeatureAttribution.pdf">Gaofei Shen - Feature Attribution techniques</a></p></li>
+<li><p><a class="reference external" href="https://raw.githubusercontent.com/interpretingdl/speech-interpretability-tutorial/refs/heads/main/book/interspeech2025/Interspeech2025_InterpretabilityTutorial_MarianneDeHeerKloots_FutureOutlook.pdf">Marianne de Heer Kloots - Key takeaways &amp; Future outlook</a></p></li>
+<li><p><a class="reference external" href="https://raw.githubusercontent.com/interpretingdl/speech-interpretability-tutorial/refs/heads/main/book/interspeech2025/Interspeech2025_InterpretabilityTutorial_WillemZuidema_Discussion.pdf">Willem Zuidema - Discussion</a></p></li>
+</ul>
+</section>
+<section id="notebooks">
+<h2>Notebooks<a class="headerlink" href="#notebooks" title="Link to this heading">#</a></h2>
 <p>We provide four notebooks, exemplifying the interpretability techniques we cover in the tutorial. The notebooks are designed to work on Google Colab, open them through the links below:</p>
 <section id="part-i-representation-understanding">
-<h2>Part I: Representation Understanding<a class="headerlink" href="#part-i-representation-understanding" title="Link to this heading">#</a></h2>
+<h3>Part I: Representation Understanding<a class="headerlink" href="#part-i-representation-understanding" title="Link to this heading">#</a></h3>
 <ul class="simple">
 <li><p><a class="reference external" href="https://colab.research.google.com/github/interpretingdl/speech-interpretability-tutorial/blob/main/book/interspeech2025/representational-analyses/probing.ipynb">Probing exercise: Does Wav2Vec2 encode vocal tract movements?</a></p></li>
 <li><p><a class="reference external" href="https://colab.research.google.com/github/interpretingdl/speech-interpretability-tutorial/blob/main/book/interspeech2025/representational-analyses/representation_space_comparisons.ipynb">Representation space comparisons: Locating acoustic and articulatory information in Wav2Vec2 with CKA</a></p></li>
 </ul>
 </section>
 <section id="part-ii-feature-importance-scoring">
-<h2>Part II: Feature Importance Scoring<a class="headerlink" href="#part-ii-feature-importance-scoring" title="Link to this heading">#</a></h2>
+<h3>Part II: Feature Importance Scoring<a class="headerlink" href="#part-ii-feature-importance-scoring" title="Link to this heading">#</a></h3>
 <ul class="simple">
 <li><p><a class="reference external" href="https://colab.research.google.com/github/interpretingdl/speech-interpretability-tutorial/blob/main/book/interspeech2025/feature-importance-scoring/context_mixing.ipynb">Context Mixing: Quantifying Context-Mixing in Speech Transformers</a></p></li>
 <li><p><a class="reference external" href="https://colab.research.google.com/github/interpretingdl/speech-interpretability-tutorial/blob/main/book/interspeech2025/feature-importance-scoring/feature_attribution.ipynb">Feature attribution: Explaining Speech Classification Models with Feature Attribution</a></p></li>
 </ul>
 </section>
+</section>
 <div class="toctree-wrapper compound">
 </div>
 </section>
@@ -454,8 +472,12 @@ <h2>Part II: Feature Importance Scoring<a class="headerlink" href="#part-ii-feat
   </div>
   <nav class="bd-toc-nav page-toc">
     <ul class="visible nav section-nav flex-column">
-<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#part-i-representation-understanding">Part I: Representation Understanding</a></li>
-<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#part-ii-feature-importance-scoring">Part II: Feature Importance Scoring</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#slides">Slides</a></li>
+<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#notebooks">Notebooks</a><ul class="nav section-nav flex-column">
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#part-i-representation-understanding">Part I: Representation Understanding</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#part-ii-feature-importance-scoring">Part II: Feature Importance Scoring</a></li>
+</ul>
+</li>
 </ul>
   </nav></div>