Update app.py

app.py

@@ -100,8 +100,8 @@ se_demo = gr.Interface(
     title = "<a href='https://github.com/modelscope/ClearerVoice-Studio' target='_blank'>ClearVoice<a/>: Speech Enhancement",
     description = ("ClearVoice ([Github Repo](https://github.com/modelscope/ClearerVoice-Studio)) is AI-powered and extracts clear speech from background noise for enhanced speech quality. It supports both 16 kHz and 48 kHz audio outputs. "
                    "To try it, simply upload your audio, or click one of the examples. "),
-    article = ("<p style='text-align: center'><a href='https://arxiv.org/abs/2206.07293' target='_blank'>FRCRN: Boosting Feature Representation Using Frequency Recurrence for Monaural Speech Enhancement</a> </p>"
-              "<p style='text-align: center'><a href='https://arxiv.org/abs/2312.11825' target='_blank'>MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation</a> </p>"),
+    article = ("<p style='text-align: center'><a href='https://arxiv.org/abs/2206.07293' target='_blank'>FRCRN: Boosting Feature Representation Using Frequency Recurrence for Monaural Speech Enhancement (ICASSP 2022)</a> </p>"
+              "<p style='text-align: center'><a href='https://arxiv.org/abs/2312.11825' target='_blank'>MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation (ICASSP 2024)</a> </p>"),
     examples = [
         ["examples/mandarin_speech_16kHz.wav", "16000 Hz"],
         ["examples/english_speech_48kHz.wav", "48000 Hz"],
@@ -121,8 +121,8 @@ ss_demo = gr.Interface(
     title = "<a href='https://github.com/modelscope/ClearerVoice-Studio' target='_blank'>ClearVoice<a/>: Speech Separation",
     description = ("ClearVoice ([Github Repo](https://github.com/modelscope/ClearerVoice-Studio)) is powered by AI and separates individual speech from mixed audio. It supports 16 kHz and two output streams. "
                     "To try it, simply upload your audio, or click one of the examples. "),
-    article = ("<p style='text-align: center'><a href='https://arxiv.org/abs/2302.11824' target='_blank'>MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions</a> </p>"
-              "<p style='text-align: center'><a href='https://arxiv.org/abs/2312.11825' target='_blank'>MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation</a> </p>"),
+    article = ("<p style='text-align: center'><a href='https://arxiv.org/abs/2302.11824' target='_blank'>MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions (ICASSP 2023)</a> </p>"
+              "<p style='text-align: center'><a href='https://arxiv.org/abs/2312.11825' target='_blank'>MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation (ICASSP 2024)</a> </p>"),
     examples = [
         ['examples/female_female_speech.wav'],
         ['examples/female_male_speech.wav'],
@@ -141,8 +141,8 @@ tse_demo = gr.Interface(
     title = "<a href='https://github.com/modelscope/ClearerVoice-Studio' target='_blank'>ClearVoice<a/>: Audio-Visual Speaker Extraction",
     description = ("ClearVoice ([Github Repo](https://github.com/modelscope/ClearerVoice-Studio)) is AI-powered and extracts each speaker's voice from a multi-speaker video using facial recognition. "
                     "To try it, simply upload your video, or click one of the examples. "),
-    # article = ("<p style='text-align: center'><a href='https://arxiv.org/abs/2302.11824' target='_blank'>MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions</a> | <a href='https://github.com/alibabasglab/MossFormer' target='_blank'>Github Repo</a></p>"
-    #           "<p style='text-align: center'><a href='https://arxiv.org/abs/2312.11825' target='_blank'>MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation</a> | <a href='https://github.com/alibabasglab/MossFormer2' target='_blank'>Github Repo</a></p>"),
+    # article = ("<p style='text-align: center'><a href='https://arxiv.org/abs/2302.11824' target='_blank'>MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions (ICASSP 2023)</a> | <a href='https://github.com/alibabasglab/MossFormer' target='_blank'>Github Repo</a></p>"
+    #           "<p style='text-align: center'><a href='https://arxiv.org/abs/2312.11825' target='_blank'>MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation (ICASSP 2024)</a> | <a href='https://github.com/alibabasglab/MossFormer2' target='_blank'>Github Repo</a></p>"),
     examples = [
         ['examples/001.mp4'],
         ['examples/002.mp4'],
@@ -162,8 +162,9 @@ sr_demo = gr.Interface(
     title = "<a href='https://github.com/modelscope/ClearerVoice-Studio' target='_blank'>ClearVoice<a/>: Speech Super Resolution",
     description = ("ClearVoice ([Github Repo](https://github.com/modelscope/ClearerVoice-Studio)) is AI-powered and transform low-resolution audio (effective sampling rate ≥ 16 kHz) into crystal-clear, high-resolution audio at 48 kHz. It supports most of audio types. "
                    "To try it, simply upload your audio, or click one of the examples. "),
-    article = ("<p style='text-align: center'><a href='https://arxiv.org/abs/2206.07293' target='_blank'>FRCRN: Boosting Feature Representation Using Frequency Recurrence for Monaural Speech Enhancement</a> </p>"
-              "<p style='text-align: center'><a href='https://arxiv.org/abs/2312.11825' target='_blank'>MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation</a> </p>"),
+    article = ("<p style='text-align: center'><a href='https://arxiv.org/abs/2206.07293' target='_blank'>FRCRN: Boosting Feature Representation Using Frequency Recurrence for Monaural Speech Enhancement (ICASSP 2022)</a> </p>"
+              "<p style='text-align: center'><a href='https://arxiv.org/abs/2312.11825' target='_blank'>MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation (ICASSP 2024)</a> </p>"
+            "<p style='text-align: center'><a href='https://arxiv.org/abs/2501.10045' target='_blank'>HiFi-SR: A Unified Generative Transformer-Convolutional Adversarial Network for High-Fidelity Speech Super-Resolution (ICASSP 2025)</a> </p>"),
     examples = [
         ["examples/mandarin_speech_16kHz.wav", True],
         ["examples/LJSpeech-001-0001-22k.wav", True],