Audio Chord Recognition with Recurrent Neural Networks

By Nicolas Boulanger-Lewandowski, Yoshua Bengio, Pascal Vincent. 2013

189 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Neural Machine Translation by Jointly Learning to Align and Translate (2014, methodology): “, Graves, 2012; Boulanger-Lewandowski et al., 2013). Sutskever et al. (2014) used this approach to generate translations from their neural machine translation model.”
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches (2014, methodology): “The beam-search to (approximately) find a sequence of maximum log-probability under RNN was proposed and used successfully in (Graves, 2012) and (Boulanger-Lewandowski et al., 2013).”
Montreal Neural Machine Translation Systems for WMT’15 (2015, positive): “4 Translations were generated by beam search, with a beam width of 20, trying to ﬁnd the sentence with the highest log-probability (single model), or highest average log-probability over all models (ensemble), divided by the sentence length (Boulanger-Lewandowski et al., 2013).”
Deep Learning: Methods and Applications (2014, methodology): “The RNN has also been recently applied to music processing applications [22, 40, 41], where the use of ReLU hidden units instead of logistic or tanh nonlinearities are explored in the RNN.”
Describing Multimedia Content Using Attention-Based Encoder-Decoder Networks (2015, background): “Instead of stochastic sampling, it is possible to approximately find a sentence sample that maximizes the probability using, for instance, beam search [8], [9].”
An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation (2018, methodology): “To this aim, we employ a different decoding strategy called Beam Search, used in previous applications of deep learning [6, 9, 21, 67].”
Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation (2014, methodology): “(3) We use an approximate beam search to search for the candidate translations fk of eij , that maximize log-likelihood log p(fk|eij) (Graves et al., 2013; Boulanger-Lewandowski et al., 2013).”
Beam Search Strategies for Neural Machine Translation (2017, methodology): “The original beam search for sequence to sequence models has been introduced and described by (Graves, 2012; Boulanger-Lewandowski et al., 2013) and by (Sutskever et al., 2014) for neural machine translation.”
A Divide-and-Conquer Approach to the Summarization of Academic Articles (2020, methodology): “At test time, we autoregressively generate a summary for each section of the input text one word at a time using simple beam search decoding [33, 34].”
Correcting Length Bias in Neural Machine Translation (2018, methodology): “Length normalization divides the score by m (Koehn and Knowles, 2017; Jean et al., 2015; Boulanger-Lewandowski et al., 2013): Google’s NMT system (Wu et al., 2016) relies on a more complicated correction: Finally, some systems add a constant word reward (He et al., 2016): If γ = 0, this reduces to…”
An End-to-End Neural Network for Polyphonic Piano Music Transcription (2015, background): “There are many experiments in MIR that suggest that rather than classifying a single frame of input, better prediction accuracies can be achieved by incorporating information over several frames of inputs [26], [33], [34].”
Neural Machine Translation: A Review (2019, methodology): “A simple method is called length normalization which divides the NMT probability by the sentence length (Jean et al., 2015b; Boulanger-Lewandowski et al., 2013):”
Few-Shot Text Generation with Pattern-Exploiting Training (2020, methodology): “To this end, we ﬁrst compute the normalized log-likelihood of y for each ( P i , d i ) as where we divide by the length of y to correct for length bias (Boulanger-Lewandowski et al., 2013; Jean et al., 2015).”
A Stable and Effective Learning Strategy for Trainable Greedy Decoding (2018, methodology): “…since the space of all possible output sequences is inﬁnite and grows exponentially with sequence length, heuristic search methods such as greedy decoding or beam search (Graves, 2012; Boulanger-Lewandowski et al., 2013) must be used at decoding time to select high-probability output sequences.”
OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation (2023, unknown): “Our OPERA is based on the Beam Search [3, 16, 37], which is a accumulated-score-based decoding strategy.”
A Divide-and-Conquer Approach to the Summarization of Long Documents (2020, methodology): “Then, we autoregressively generate a summary for each section of the input text using simple beam search decoding [48], [49] and compose the complete summary by concatenating the individual summaries.”
On NMT Search Errors and Model Errors: Cat Got Your Tongue? (2019, methodology): “A popular method to counter the length bias in NMT is length normalization (Jean et al., 2015; Boulanger-Lewandowski et al., 2013) which simply divides the sentence score by the sentence length.”