Update documentation

Author: mdhk

_sources/index.md

@@ -34,13 +34,13 @@ We will present our tutorial about _Interpretability Techniques for Speech Model
 
 **Representational Analysis methods**: 
 - Probing{cite}`cormacenglishDomainInformedProbingWav2vec2022, choEvidenceVocalTract2023,bentumProcessingStressEndEnd2024,shen-etal-2024-encoding,bentum25_interspeech,deheerklootsWhatSelfsupervisedSpeech2025,cormacenglishDomainInformedProbingWav2vec2022`
-- Representation space comparisons: RSA{cite}`chrupala-etal-2020-analyzing,shenWaveSyntaxProbing2023a`, CCA{cite}`Pasad2021`, CKA{cite}`pmlr-v97-kornblith19a`)
+- Representation space comparisons: RSA{cite}`chrupala-etal-2020-analyzing,shenWaveSyntaxProbing2023a`, CCA{cite}`Pasad2021`, CKA{cite}`pmlr-v97-kornblith19a`
 - CTC & Decoder lenses{cite}`deheerklootsHumanlikeLinguisticBiases2024,langedijkDecoderLensLayerwiseInterpretation2024` 
 - Embedding similarities (ABX tests){cite}`schatz2016,algayresDPParseFindingWord2022,seysselDiscriminatingFormMeaning2025` 
 
 **Feature Importance Scoring methods**: 
 - Context-mixing: Attention{cite}`yangUnderstandingSelfAttentionSelfSupervised2020a,shimUNDERSTANDINGROLESELF2022,alastrueyLocalityAttentionDirect2022,audhkhasiAnalysisSelfAttentionHead2022`, Attention Norm{cite}`kobayashiAttentionNotOnly2020a`, Value-Zeroing {cite}`mohebbiHomophoneDisambiguationReveals2023a`
-- Feature attribution {cite}`fucciExplainabilitySpeechModels2024,shenReliabilityFeatureAttribution2025`: Gradient-based{cite}`prasadHowAccentsConfound2020,guptaPhonemeDiscretizedSaliency2024` & Perturbation-based{cite}`wuExplanationsforASR2023,pastor-etal-2024-explaining`
+- Feature attribution{cite}`fucciExplainabilitySpeechModels2024,shenReliabilityFeatureAttribution2025`: Gradient-based{cite}`prasadHowAccentsConfound2020,guptaPhonemeDiscretizedSaliency2024` & Perturbation-based{cite}`wuExplanationsforASR2023,pastor-etal-2024-explaining`
 
 ## References
 

_sources/interspeech2025/intro.md

@@ -1,4 +1,4 @@
-# Interspeech 2025
+# Interspeech 2025 tutorial
 
 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:
 

_sources/reading-list.md

@@ -0,0 +1,3 @@
+# Reading list
+
+In [this github repository](https://github.com/mdhk/awesome-speech-interpretability) we share an annotated bibliography we are compiling while surveying interpretability analyses of speech processing models. Your suggestions are very welcome!

genindex.html

@@ -177,9 +177,9 @@
                 </a>
             </li>
         </ul>
-        <p aria-level="2" class="caption" role="heading"><span class="caption-text">Tutorial Materials</span></p>
+        <p aria-level="2" class="caption" role="heading"><span class="caption-text">Materials</span></p>
 <ul class="nav bd-sidenav">
-<li class="toctree-l1 has-children"><a class="reference internal" href="interspeech2025/intro.html">Interspeech 2025</a><input class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-1"><i class="fa-solid fa-chevron-down"></i></label><ul>
+<li class="toctree-l1 has-children"><a class="reference internal" href="interspeech2025/intro.html">Interspeech 2025 tutorial</a><input class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-1"><i class="fa-solid fa-chevron-down"></i></label><ul>
 <li class="toctree-l2"><a class="reference internal" href="interspeech2025/representational-analyses/probing.html">Probing exercise: Does Wav2Vec2 encode vocal tract movements?</a></li>
 
 
@@ -206,6 +206,7 @@
 
 </ul>
 </li>
+<li class="toctree-l1"><a class="reference internal" href="reading-list.html">Reading list</a></li>
 </ul>
 
     </div>

index.html

@@ -74,7 +74,7 @@
   <link rel="icon" href="_static/favicon.ico" />
   <link rel="index" title="Index" href="genindex.html" />
   <link rel="search" title="Search" href="search.html" />
-  <link rel="next" title="Interspeech 2025" href="interspeech2025/intro.html" />
+  <link rel="next" title="Interspeech 2025 tutorial" href="interspeech2025/intro.html" />
   <meta name="viewport" content="width=device-width, initial-scale=1" />
   <meta name="docsearch:language" content="en" />
 </head>
@@ -181,11 +181,10 @@
                     </a>
                   </li>
                 </ul>
-                <p aria-level="2" class="caption" role="heading"><span class="caption-text">Tutorial Materials</span>
-                </p>
+                <p aria-level="2" class="caption" role="heading"><span class="caption-text">Materials</span></p>
                 <ul class="nav bd-sidenav">
                   <li class="toctree-l1 has-children"><a class="reference internal"
-                      href="interspeech2025/intro.html">Interspeech 2025</a><input class="toctree-checkbox"
+                      href="interspeech2025/intro.html">Interspeech 2025 tutorial</a><input class="toctree-checkbox"
                       id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox" /><label class="toctree-toggle"
                       for="toctree-checkbox-1"><i class="fa-solid fa-chevron-down"></i></label>
                     <ul>
@@ -224,6 +223,7 @@
 
                     </ul>
                   </li>
+                  <li class="toctree-l1"><a class="reference internal" href="reading-list.html">Reading list</a></li>
                 </ul>
 
               </div>
@@ -647,7 +647,7 @@ <h2>Tutorial contents<a class="headerlink" href="#tutorial-contents"
                         CCA<span id="id3"><sup><a class="reference internal" href="#id20"
                               title="Ankita Pasad, Ju-Chieh Chou, and Karen Livescu. Layer-wise analysis of a self-supervised speech representation model. In 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), volume, 914-921. 2021. doi:10.1109/ASRU51503.2021.9688093.">9</a></sup></span>,
                         CKA<span id="id4"><sup><a class="reference internal" href="#id21"
-                              title="Simon Kornblith, Mohammad Norouzi, Honglak Lee, and Geoffrey Hinton. Similarity of neural network representations revisited. In Kamalika Chaudhuri and Ruslan Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, 3519–3529. PMLR, 09–15 Jun 2019. URL: https://proceedings.mlr.press/v97/kornblith19a.html.">10</a></sup></span>)
+                              title="Simon Kornblith, Mohammad Norouzi, Honglak Lee, and Geoffrey Hinton. Similarity of neural network representations revisited. In Kamalika Chaudhuri and Ruslan Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, 3519–3529. PMLR, 09–15 Jun 2019. URL: https://proceedings.mlr.press/v97/kornblith19a.html.">10</a></sup></span>
                       </p>
                     </li>
                     <li>
@@ -686,7 +686,7 @@ <h2>Tutorial contents<a class="headerlink" href="#tutorial-contents"
                       </p>
                     </li>
                     <li>
-                      <p>Feature attribution <span id="id10"><sup><a class="reference internal" href="#id30"
+                      <p>Feature attribution<span id="id10"><sup><a class="reference internal" href="#id30"
                               title="Dennis Fucci, Beatrice Savoldi, Marco Gaido, Matteo Negri, Mauro Cettolo, and Luisa Bentivogli. Explainability for Speech Models: On the Challenges of Acoustic Feature Selection. In Felice Dell'Orletta, Alessandro Lenci, Simonetta Montemagni, and Rachele Sprugnoli, editors, Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024), 373–381. Pisa, Italy, December 2024. CEUR Workshop Proceedings.">22</a>,<a
                               class="reference internal" href="#id31"
                               title="Gaofei Shen, Hosein Mohebbi, Arianna Bisazza, Afra Alishahi, and Grzegorz Chrupała. On the reliability of feature attribution methods for speech classification. In Interspeech 2025. 2025. doi:10.48550/arXiv.2505.16406.">23</a></sup></span>:
@@ -1014,7 +1014,7 @@ <h2>References<a class="headerlink" href="#references" title="Link to this headi
                 <a class="right-next" href="interspeech2025/intro.html" title="next page">
                   <div class="prev-next-info">
                     <p class="prev-next-subtitle">next</p>
-                    <p class="prev-next-title">Interspeech 2025</p>
+                    <p class="prev-next-title">Interspeech 2025 tutorial</p>
                   </div>
                   <i class="fa-solid fa-angle-right"></i>
                 </a>

interspeech2025/feature-importance-scoring/context_mixing.html

@@ -180,9 +180,9 @@
                 </a>
             </li>
         </ul>
-        <p aria-level="2" class="caption" role="heading"><span class="caption-text">Tutorial Materials</span></p>
+        <p aria-level="2" class="caption" role="heading"><span class="caption-text">Materials</span></p>
 <ul class="current nav bd-sidenav">
-<li class="toctree-l1 current active has-children"><a class="reference internal" href="../intro.html">Interspeech 2025</a><input checked="" class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-1"><i class="fa-solid fa-chevron-down"></i></label><ul class="current">
+<li class="toctree-l1 current active has-children"><a class="reference internal" href="../intro.html">Interspeech 2025 tutorial</a><input checked="" class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-1"><i class="fa-solid fa-chevron-down"></i></label><ul class="current">
 <li class="toctree-l2"><a class="reference internal" href="../representational-analyses/probing.html">Probing exercise: Does Wav2Vec2 encode vocal tract movements?</a></li>
 
 
@@ -209,6 +209,7 @@
 
 </ul>
 </li>
+<li class="toctree-l1"><a class="reference internal" href="../../reading-list.html">Reading list</a></li>
 </ul>
 
     </div>

interspeech2025/feature-importance-scoring/feature_attribution.html

@@ -62,6 +62,7 @@
     <link rel="icon" href="../../_static/favicon.ico"/>
     <link rel="index" title="Index" href="../../genindex.html" />
     <link rel="search" title="Search" href="../../search.html" />
+    <link rel="next" title="Reading list" href="../../reading-list.html" />
     <link rel="prev" title="Quantifying Context-Mixing in Speech Transformers" href="context_mixing.html" />
   <meta name="viewport" content="width=device-width, initial-scale=1"/>
   <meta name="docsearch:language" content="en"/>
@@ -177,9 +178,9 @@
                 </a>
             </li>
         </ul>
-        <p aria-level="2" class="caption" role="heading"><span class="caption-text">Tutorial Materials</span></p>
+        <p aria-level="2" class="caption" role="heading"><span class="caption-text">Materials</span></p>
 <ul class="current nav bd-sidenav">
-<li class="toctree-l1 current active has-children"><a class="reference internal" href="../intro.html">Interspeech 2025</a><input checked="" class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-1"><i class="fa-solid fa-chevron-down"></i></label><ul class="current">
+<li class="toctree-l1 current active has-children"><a class="reference internal" href="../intro.html">Interspeech 2025 tutorial</a><input checked="" class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-1"><i class="fa-solid fa-chevron-down"></i></label><ul class="current">
 <li class="toctree-l2"><a class="reference internal" href="../representational-analyses/probing.html">Probing exercise: Does Wav2Vec2 encode vocal tract movements?</a></li>
 
 
@@ -206,6 +207,7 @@
 
 </ul>
 </li>
+<li class="toctree-l1"><a class="reference internal" href="../../reading-list.html">Reading list</a></li>
 </ul>
 
     </div>
@@ -970,6 +972,15 @@ <h1>Last words:<a class="headerlink" href="#last-words" title="Link to this head
         <p class="prev-next-title">Quantifying Context-Mixing in Speech Transformers</p>
       </div>
     </a>
+    <a class="right-next"
+       href="../../reading-list.html"
+       title="next page">
+      <div class="prev-next-info">
+        <p class="prev-next-subtitle">next</p>
+        <p class="prev-next-title">Reading list</p>
+      </div>
+      <i class="fa-solid fa-angle-right"></i>
+    </a>
 </div>
                 </footer>
 

interspeech2025/intro.html

@@ -8,7 +8,7 @@
     <meta charset="utf-8" />
     <meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.18.1: http://docutils.sourceforge.net/" />
 
-    <title>Interspeech 2025 &#8212; Tutorial @ Interspeech 2025</title>
+    <title>Interspeech 2025 tutorial &#8212; Tutorial @ Interspeech 2025</title>
 
 
 
@@ -178,9 +178,9 @@
                 </a>
             </li>
         </ul>
-        <p aria-level="2" class="caption" role="heading"><span class="caption-text">Tutorial Materials</span></p>
+        <p aria-level="2" class="caption" role="heading"><span class="caption-text">Materials</span></p>
 <ul class="current nav bd-sidenav">
-<li class="toctree-l1 current active has-children"><a class="current reference internal" href="#">Interspeech 2025</a><input checked="" class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-1"><i class="fa-solid fa-chevron-down"></i></label><ul>
+<li class="toctree-l1 current active has-children"><a class="current reference internal" href="#">Interspeech 2025 tutorial</a><input checked="" class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-1"><i class="fa-solid fa-chevron-down"></i></label><ul>
 <li class="toctree-l2"><a class="reference internal" href="representational-analyses/probing.html">Probing exercise: Does Wav2Vec2 encode vocal tract movements?</a></li>
 
 
@@ -207,6 +207,7 @@
 
 </ul>
 </li>
+<li class="toctree-l1"><a class="reference internal" href="../reading-list.html">Reading list</a></li>
 </ul>
 
     </div>
@@ -345,7 +346,7 @@
 
 
 <div id="jb-print-docs-body" class="onlyprint">
-    <h1>Interspeech 2025</h1>
+    <h1>Interspeech 2025 tutorial</h1>
     <!-- Table of contents -->
     <div id="print-main-content">
         <div id="jb-print-toc">
@@ -368,8 +369,8 @@ <h2> Contents </h2>
 <div id="searchbox"></div>
                 <article class="bd-article">
 
-  <section class="tex2jax_ignore mathjax_ignore" id="interspeech-2025">
-<h1>Interspeech 2025<a class="headerlink" href="#interspeech-2025" title="Link to this heading">#</a></h1>
+  <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>
 <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>

interspeech2025/representational-analyses/probing.html

@@ -63,7 +63,7 @@
     <link rel="index" title="Index" href="../../genindex.html" />
     <link rel="search" title="Search" href="../../search.html" />
     <link rel="next" title="Representation space comparisons: Locating acoustic and articulatory information in Wav2Vec2 with CKA" href="representation_space_comparisons.html" />
-    <link rel="prev" title="Interspeech 2025" href="../intro.html" />
+    <link rel="prev" title="Interspeech 2025 tutorial" href="../intro.html" />
   <meta name="viewport" content="width=device-width, initial-scale=1"/>
   <meta name="docsearch:language" content="en"/>
   </head>
@@ -178,9 +178,9 @@
                 </a>
             </li>
         </ul>
-        <p aria-level="2" class="caption" role="heading"><span class="caption-text">Tutorial Materials</span></p>
+        <p aria-level="2" class="caption" role="heading"><span class="caption-text">Materials</span></p>
 <ul class="current nav bd-sidenav">
-<li class="toctree-l1 current active has-children"><a class="reference internal" href="../intro.html">Interspeech 2025</a><input checked="" class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-1"><i class="fa-solid fa-chevron-down"></i></label><ul class="current">
+<li class="toctree-l1 current active has-children"><a class="reference internal" href="../intro.html">Interspeech 2025 tutorial</a><input checked="" class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-1"><i class="fa-solid fa-chevron-down"></i></label><ul class="current">
 <li class="toctree-l2 current active"><a class="current reference internal" href="#">Probing exercise: Does Wav2Vec2 encode vocal tract movements?</a></li>
 
 
@@ -207,6 +207,7 @@
 
 </ul>
 </li>
+<li class="toctree-l1"><a class="reference internal" href="../../reading-list.html">Reading list</a></li>
 </ul>
 
     </div>
@@ -2926,7 +2927,7 @@ <h1>Outlook<a class="headerlink" href="#outlook" title="Link to this heading">#<
       <i class="fa-solid fa-angle-left"></i>
       <div class="prev-next-info">
         <p class="prev-next-subtitle">previous</p>
-        <p class="prev-next-title">Interspeech 2025</p>
+        <p class="prev-next-title">Interspeech 2025 tutorial</p>
       </div>
     </a>
     <a class="right-next"

interspeech2025/representational-analyses/representation_space_comparisons.html

@@ -178,9 +178,9 @@
                 </a>
             </li>
         </ul>
-        <p aria-level="2" class="caption" role="heading"><span class="caption-text">Tutorial Materials</span></p>
+        <p aria-level="2" class="caption" role="heading"><span class="caption-text">Materials</span></p>
 <ul class="current nav bd-sidenav">
-<li class="toctree-l1 current active has-children"><a class="reference internal" href="../intro.html">Interspeech 2025</a><input checked="" class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-1"><i class="fa-solid fa-chevron-down"></i></label><ul class="current">
+<li class="toctree-l1 current active has-children"><a class="reference internal" href="../intro.html">Interspeech 2025 tutorial</a><input checked="" class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-1"><i class="fa-solid fa-chevron-down"></i></label><ul class="current">
 <li class="toctree-l2"><a class="reference internal" href="probing.html">Probing exercise: Does Wav2Vec2 encode vocal tract movements?</a></li>
 
 
@@ -207,6 +207,7 @@
 
 </ul>
 </li>
+<li class="toctree-l1"><a class="reference internal" href="../../reading-list.html">Reading list</a></li>
 </ul>
 
     </div>