1 | /* Copyright 2017 The TensorFlow Authors. All Rights Reserved. |
2 | |
3 | Licensed under the Apache License, Version 2.0 (the "License"); |
4 | you may not use this file except in compliance with the License. |
5 | You may obtain a copy of the License at |
6 | |
7 | http://www.apache.org/licenses/LICENSE-2.0 |
8 | |
9 | Unless required by applicable law or agreed to in writing, software |
10 | distributed under the License is distributed on an "AS IS" BASIS, |
11 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
12 | See the License for the specific language governing permissions and |
13 | limitations under the License. |
14 | ==============================================================================*/ |
15 | |
16 | // Basic class for computing MFCCs from spectrogram slices. |
17 | |
18 | #ifndef TENSORFLOW_CORE_KERNELS_MFCC_H_ |
19 | #define TENSORFLOW_CORE_KERNELS_MFCC_H_ |
20 | |
21 | #include <vector> |
22 | |
23 | #include "tensorflow/core/framework/op_kernel.h" |
24 | #include "tensorflow/core/kernels/mfcc_dct.h" |
25 | #include "tensorflow/core/kernels/mfcc_mel_filterbank.h" |
26 | #include "tensorflow/core/platform/logging.h" |
27 | |
28 | namespace tensorflow { |
29 | |
30 | class Mfcc { |
31 | public: |
32 | Mfcc(); |
33 | bool Initialize(int input_length, double input_sample_rate); |
34 | |
35 | // Input is a single squared-magnitude spectrogram frame. The input spectrum |
36 | // is converted to linear magnitude and weighted into bands using a |
37 | // triangular mel filterbank, and a discrete cosine transform (DCT) of the |
38 | // values is taken. Output is populated with the lowest dct_coefficient_count |
39 | // of these values. |
40 | void Compute(const std::vector<double>& spectrogram_frame, |
41 | std::vector<double>* output) const; |
42 | |
43 | void set_upper_frequency_limit(double upper_frequency_limit) { |
44 | CHECK(!initialized_) << "Set frequency limits before calling Initialize." ; |
45 | upper_frequency_limit_ = upper_frequency_limit; |
46 | } |
47 | |
48 | void set_lower_frequency_limit(double lower_frequency_limit) { |
49 | CHECK(!initialized_) << "Set frequency limits before calling Initialize." ; |
50 | lower_frequency_limit_ = lower_frequency_limit; |
51 | } |
52 | |
53 | void set_filterbank_channel_count(int filterbank_channel_count) { |
54 | CHECK(!initialized_) << "Set channel count before calling Initialize." ; |
55 | filterbank_channel_count_ = filterbank_channel_count; |
56 | } |
57 | |
58 | void set_dct_coefficient_count(int dct_coefficient_count) { |
59 | CHECK(!initialized_) << "Set coefficient count before calling Initialize." ; |
60 | dct_coefficient_count_ = dct_coefficient_count; |
61 | } |
62 | |
63 | private: |
64 | MfccMelFilterbank mel_filterbank_; |
65 | MfccDct dct_; |
66 | bool initialized_; |
67 | double lower_frequency_limit_; |
68 | double upper_frequency_limit_; |
69 | int filterbank_channel_count_; |
70 | int dct_coefficient_count_; |
71 | TF_DISALLOW_COPY_AND_ASSIGN(Mfcc); |
72 | }; |
73 | |
74 | } // namespace tensorflow |
75 | |
76 | #endif // TENSORFLOW_CORE_KERNELS_MFCC_H_ |
77 | |