[I2S][SR] Add new I2S library and Sound Recognition support

CMakeLists.txt

@@ -82,6 +82,9 @@ set(LIBRARY_SRCS
   libraries/BluetoothSerial/src/BTScanResultsSet.cpp
   libraries/DNSServer/src/DNSServer.cpp
   libraries/EEPROM/src/EEPROM.cpp
+  libraries/ESP_I2S/src/ESP_I2S.cpp
+  libraries/ESP_SR/src/ESP_SR.cpp
+  libraries/ESP_SR/src/esp32-hal-sr.c
   libraries/ESPmDNS/src/ESPmDNS.cpp
   libraries/Ethernet/src/ETH.cpp
   libraries/FFat/src/FFat.cpp
@@ -91,7 +94,6 @@ set(LIBRARY_SRCS
   libraries/HTTPUpdate/src/HTTPUpdate.cpp
   libraries/LittleFS/src/LittleFS.cpp
   libraries/Insights/src/Insights.cpp
-  libraries/I2S/src/I2S.cpp
   libraries/NetBIOS/src/NetBIOS.cpp
   libraries/Preferences/src/Preferences.cpp
   libraries/RainMaker/src/RMaker.cpp

libraries/ESP_I2S/keywords.txt

@@ -0,0 +1,21 @@
+#######################################
+# Syntax Coloring Map For ESP_I2S
+#######################################
+
+#######################################
+# Datatypes (KEYWORD1)
+#######################################
+
+ESP_I2S	KEYWORD1
+
+#######################################
+# Methods and Functions (KEYWORD2)
+#######################################
+
+onEvent	KEYWORD2
+
+#######################################
+# Constants (LITERAL1)
+#######################################
+
+SR_EVENT_WAKEWORD	LITERAL1

libraries/ESP_I2S/library.properties

@@ -0,0 +1,9 @@
+name=ESP_I2S
+version=1.0.0
+author=me-no-dev
+maintainer=me-no-dev
+sentence=Library for ESP I2S communication
+paragraph=Supports ESP32 Arduino platforms.
+category=Sound
+url=https://github.com/espressif/arduino-esp32/
+architectures=esp32

libraries/ESP_I2S/src/ESP_I2S.h

@@ -0,0 +1,104 @@
+#pragma once
+#include "Arduino.h"
+#include "esp_err.h"
+#include "driver/i2s_std.h"
+#include "driver/i2s_tdm.h"
+#include "driver/i2s_pdm.h"
+#include "soc/soc_caps.h"
+
+typedef esp_err_t (*i2s_channel_read_fn)(i2s_chan_handle_t handle, char * tmp_buf, void *dest, size_t size, size_t *bytes_read, uint32_t timeout_ms);
+
+typedef enum {
+    I2S_MODE_STD,
+    I2S_MODE_TDM,
+    I2S_MODE_PDM_TX,
+    I2S_MODE_PDM_RX
+} i2s_mode_t;
+
+typedef enum {
+    I2S_RX_TRANSFORM_NONE,
+    I2S_RX_TRANSFORM_32_TO_16,
+    I2S_RX_TRANSFORM_16_STEREO_TO_MONO,
+    I2S_RX_TRANSFORM_MAX
+} i2s_rx_transform_t;
+
+class I2SClass: public Stream {
+  public:
+    I2SClass();
+    ~I2SClass();
+
+    //STD + TDM mode
+    void setPins(int8_t bclk, int8_t ws, int8_t dout, int8_t din=-1, int8_t mclk=-1);
+    void setInverted(bool bclk, bool ws, bool mclk=false);
+
+    //PDM TX + PDM RX mode
+    void setPinsPdmTx(int8_t clk, int8_t dout0, int8_t dout1);
+    void setPinsPdmRx(int8_t clk, int8_t din0, int8_t din1, int8_t din2, int8_t din3);
+    void setInvertedPdm(bool clk);
+
+    bool begin(i2s_mode_t mode, uint32_t rate, i2s_data_bit_width_t bits_cfg, i2s_slot_mode_t ch);
+    bool configureTX(uint32_t rate, i2s_data_bit_width_t bits_cfg, i2s_slot_mode_t ch);
+    bool configureRX(uint32_t rate, i2s_data_bit_width_t bits_cfg, i2s_slot_mode_t ch, i2s_rx_transform_t transform=I2S_RX_TRANSFORM_NONE);
+    bool end();
+
+    size_t readBytes(char *buffer, size_t size);
+    size_t write(uint8_t *buffer, size_t size);
+
+    i2s_chan_handle_t txChan();
+    uint32_t txSampleRate();
+    i2s_data_bit_width_t txDataWidth();
+    i2s_slot_mode_t txSlotMode();
+
+    i2s_chan_handle_t rxChan();
+    uint32_t rxSampleRate();
+    i2s_data_bit_width_t rxDataWidth();
+    i2s_slot_mode_t rxSlotMode();
+
+    int lastError();
+
+    int available();
+    int peek();
+    int read();
+    size_t write(uint8_t d);
+
+    // Record short PCM WAV to memory with current RX settings. Returns buffer that must be freed by the user.
+    uint8_t * recordWAV(size_t rec_seconds, size_t * out_size);
+    // Play short PCM WAV from memory
+    void playWAV(uint8_t * data, size_t len);
+    // Play short MP3 from memory
+    bool playMP3(uint8_t *src, size_t src_len);
+
+
+  private:
+    esp_err_t last_error;
+    i2s_mode_t _mode;
+
+    i2s_chan_handle_t tx_chan;
+    uint32_t tx_sample_rate;
+    i2s_data_bit_width_t tx_data_bit_width;
+    i2s_slot_mode_t tx_slot_mode;
+
+    i2s_channel_read_fn rx_fn;
+    i2s_rx_transform_t rx_transform;
+    char * rx_transform_buf;
+    size_t rx_transform_buf_len;
+
+    i2s_chan_handle_t rx_chan;
+    uint32_t rx_sample_rate;
+    i2s_data_bit_width_t rx_data_bit_width;
+    i2s_slot_mode_t rx_slot_mode;
+
+    //STD and TDM mode
+    int8_t _mclk, _bclk, _ws, _dout, _din;
+    bool _mclk_inv, _bclk_inv, _ws_inv;
+
+    //PDM mode
+    int8_t _rx_clk, _rx_din0, _rx_din1, _rx_din2, _rx_din3; //TODO: soc_caps.h 1/4
+    bool _rx_clk_inv;
+    int8_t _tx_clk, _tx_dout0, _tx_dout1;
+    bool _tx_clk_inv;
+
+    bool allocTranformRX(size_t buf_len);
+    bool transformRX(i2s_rx_transform_t transform);
+    static bool i2sDetachBus(void * bus_pointer);
+};

libraries/ESP_I2S/src/wav_header.h

@@ -0,0 +1,91 @@
+#pragma once
+#include <stdint.h>
+
+/**
+ * @brief Header structure for WAV file with only one data chunk
+ *
+ * @note See this for reference: http://soundfile.sapp.org/doc/WaveFormat/
+ *
+ * @note Assignment to variables in this struct directly is only possible for little endian architectures
+ *       (including Xtensa & RISC-V)
+ */
+
+typedef struct {
+    char chunk_id[4];         /*!< Contains the letters "RIFF" in ASCII form */
+    uint32_t chunk_size;      /*!< This is the size of the rest of the chunk following this number */
+    char chunk_format[4];     /*!< Contains the letters "WAVE" */
+} __attribute__((packed)) wav_descriptor_chunk_t; /*!< Canonical WAVE format starts with the RIFF header */
+
+typedef struct {
+    char subchunk_id[4];      /*!< Contains the letters "fmt " */
+    uint32_t subchunk_size;   /*!< PCM = 16, This is the size of the rest of the Subchunk which follows this number */
+    uint16_t audio_format;    /*!< PCM = 1, values other than 1 indicate some form of compression */
+    uint16_t num_of_channels; /*!< Mono = 1, Stereo = 2, etc. */
+    uint32_t sample_rate;     /*!< 8000, 44100, etc. */
+    uint32_t byte_rate;       /*!< ==SampleRate * NumChannels * BitsPerSample s/ 8 */
+    uint16_t block_align;     /*!< ==NumChannels * BitsPerSample / 8 */
+    uint16_t bits_per_sample; /*!< 8 bits = 8, 16 bits = 16, etc. */
+} __attribute__((packed)) pcm_wav_fmt_chunk_t; /*!< The "fmt " subchunk describes the sound data's format */
+
+typedef struct {
+    char subchunk_id[4];      /*!< Contains the letters "fmt " */
+    uint32_t subchunk_size;   /*!< ALAW/MULAW = 18, This is the size of the rest of the Subchunk which follows this number */
+    uint16_t audio_format;    /*!< ALAW = 6, MULAW = 7, values other than 1 indicate some form of compression */
+    uint16_t num_of_channels; /*!< ALAW/MULAW = 1, Mono = 1, Stereo = 2, etc. */
+    uint32_t sample_rate;     /*!< ALAW/MULAW = 8000, 8000, 44100, etc. */
+    uint32_t byte_rate;       /*!< ALAW/MULAW = 8000, ==SampleRate * NumChannels * BitsPerSample s/ 8 */
+    uint16_t block_align;     /*!< ALAW/MULAW = 1, ==NumChannels * BitsPerSample / 8 */
+    uint16_t bits_per_sample; /*!< ALAW/MULAW = 8, 8 bits = 8, 16 bits = 16, etc. */
+    uint16_t ext_size;        /*!< ALAW/MULAW = 0, Size of the extension (0 or 22) */
+} __attribute__((packed)) non_pcm_wav_fmt_chunk_t; /*!< The "fmt " subchunk describes the sound data's format */
+
+typedef struct {
+    char subchunk_id[4];      /*!< Contains the letters "data" */
+    uint32_t subchunk_size;   /*!< ==NumSamples * NumChannels * BitsPerSample / 8 */
+} __attribute__((packed)) wav_data_chunk_t; /*!< The "data" subchunk contains the size of the data and the actual sound */
+
+typedef struct {
+    wav_descriptor_chunk_t descriptor_chunk;  /*!< Canonical WAVE format starts with the RIFF header */
+    pcm_wav_fmt_chunk_t fmt_chunk;            /*!< The "fmt " subchunk describes the sound data's format */
+    wav_data_chunk_t data_chunk;              /*!< The "data" subchunk contains the size of the data and the actual sound */
+} __attribute__((packed)) pcm_wav_header_t;
+
+typedef struct {
+    wav_descriptor_chunk_t descriptor_chunk;  /*!< Canonical WAVE format starts with the RIFF header */
+    non_pcm_wav_fmt_chunk_t fmt_chunk;        /*!< The "fmt " subchunk describes the sound data's format */
+    wav_data_chunk_t data_chunk;              /*!< The "data" subchunk contains the size of the data and the actual sound */
+} __attribute__((packed)) non_pcm_wav_header_t;
+
+#define WAVE_FORMAT_PCM         1 // PCM
+#define WAVE_FORMAT_IEEE_FLOAT  3 // IEEE float
+#define WAVE_FORMAT_ALAW        6 // 8-bit ITU-T G.711 A-law
+#define WAVE_FORMAT_MULAW       7 // 8-bit ITU-T G.711 µ-law
+
+#define PCM_WAV_HEADER_SIZE     44
+#define NON_PCM_WAV_HEADER_SIZE 46
+
+/**
+ * @brief Default header for PCM format WAV files
+ *
+ */
+#define PCM_WAV_HEADER_DEFAULT(wav_sample_size, wav_sample_bits, wav_sample_rate, wav_channel_num) { \
+    .descriptor_chunk = { \
+        .chunk_id = {'R', 'I', 'F', 'F'}, \
+        .chunk_size = (wav_sample_size) + sizeof(pcm_wav_header_t) - 8, \
+        .chunk_format = {'W', 'A', 'V', 'E'} \
+    }, \
+    .fmt_chunk = { \
+        .subchunk_id = {'f', 'm', 't', ' '}, \
+        .subchunk_size = 16, /* 16 for PCM */ \
+        .audio_format = WAVE_FORMAT_PCM, /* 1 for PCM */ \
+        .num_of_channels = (uint16_t)(wav_channel_num), \
+        .sample_rate = (wav_sample_rate), \
+        .byte_rate = (wav_sample_bits) * (wav_sample_rate) * (wav_channel_num) / 8, \
+        .block_align = (uint16_t)((wav_sample_bits) * (wav_channel_num) / 8), \
+        .bits_per_sample = (uint16_t)(wav_sample_bits)\
+    }, \
+    .data_chunk = { \
+        .subchunk_id = {'d', 'a', 't', 'a'}, \
+        .subchunk_size = (wav_sample_size) \
+    } \
+}

libraries/ESP_SR/examples/Basic/Basic.ino

@@ -0,0 +1,92 @@
+
+#include "ESP_I2S.h"
+#include "ESP_SR.h"
+
+#define I2S_PIN_BCK 17
+#define I2S_PIN_WS  47
+#define I2S_PIN_DIN 16
+
+#define LIGHT_PIN   40
+#define FAN_PIN     41
+
+I2SClass i2s;
+
+// Generated using the following command:
+// python3 tools/gen_sr_commands.py "Turn on the light,Switch on the light;Turn off the light,Switch off the light,Go dark;Start fan;Stop fan"
+enum {
+  SR_CMD_TURN_ON_THE_LIGHT,
+  SR_CMD_TURN_OFF_THE_LIGHT,
+  SR_CMD_START_FAN,
+  SR_CMD_STOP_FAN,
+};
+static const sr_cmd_t sr_commands[] = {
+  { 0, "Turn on the light", "TkN nN jc LiT"},
+  { 0, "Switch on the light", "SWgp nN jc LiT"},
+  { 1, "Turn off the light", "TkN eF jc LiT"},
+  { 1, "Switch off the light", "SWgp eF jc LiT"},
+  { 1, "Go dark", "Gb DnRK"},
+  { 2, "Start fan", "STnRT FaN"},
+  { 3, "Stop fan", "STnP FaN"},
+};
+
+void onSrEvent(sr_event_t event, int command_id, int phrase_id){
+  switch(event){
+    case SR_EVENT_WAKEWORD:
+      Serial.println("WakeWord Detected!");
+      break;
+    case SR_EVENT_WAKEWORD_CHANNEL:
+      Serial.printf("WakeWord Channel %d Verified!\n", command_id);
+      ESP_SR.setMode(SR_MODE_COMMAND); // Switch to Command detection
+      break;
+    case SR_EVENT_TIMEOUT:
+      Serial.println("Timeout Detected!");
+      ESP_SR.setMode(SR_MODE_WAKEWORD); // Switch back to WakeWord detection
+      break;
+    case SR_EVENT_COMMAND:
+      Serial.printf("Command %d Detected! %s\n", command_id, sr_commands[phrase_id].str);
+      switch(command_id){
+	      case SR_CMD_TURN_ON_THE_LIGHT:
+	      	digitalWrite(LIGHT_PIN, HIGH);
+	      	break;
+	      case SR_CMD_TURN_OFF_THE_LIGHT:
+	      	digitalWrite(LIGHT_PIN, LOW);
+	      	break;
+	      case SR_CMD_START_FAN:
+	      	digitalWrite(FAN_PIN, HIGH);
+	      	break;
+	      case SR_CMD_STOP_FAN:
+	      	digitalWrite(FAN_PIN, LOW);
+	      	break;
+	      default:
+	      	Serial.println("Unknown Command!");
+	      	break;
+      }
+      ESP_SR.setMode(SR_MODE_COMMAND); // Allow for more commands to be given, before timeout
+      // ESP_SR.setMode(SR_MODE_WAKEWORD); // Switch back to WakeWord detection
+      break;
+    default:
+      Serial.println("Unknown Event!");
+      break;
+  }
+}
+
+void setup(){
+  Serial.begin(115200);
+
+  pinMode(LIGHT_PIN, OUTPUT);
+  digitalWrite(LIGHT_PIN, LOW);
+  pinMode(FAN_PIN, OUTPUT);
+  digitalWrite(FAN_PIN, LOW);
+
+  i2s.setPins(I2S_PIN_BCK, I2S_PIN_WS, -1, I2S_PIN_DIN);
+  i2s.setTimeout(1000);
+  i2s.begin(16000, I2S_DATA_BIT_WIDTH_16BIT, I2S_SLOT_MODE_STEREO);
+
+
+  ESP_SR.onEvent(onSrEvent);
+  ESP_SR.begin(i2s, sr_commands, sizeof(sr_commands) / sizeof(sr_cmd_t), SR_CHANNELS_STEREO, SR_MODE_WAKEWORD);
+}
+
+void loop(){
+
+}

libraries/ESP_SR/keywords.txt

@@ -0,0 +1,40 @@
+#######################################
+# Syntax Coloring Map For ESP_SR
+#######################################
+
+#######################################
+# Datatypes (KEYWORD1)
+#######################################
+
+ESP_SR	KEYWORD1
+ESP_SR_Class	KEYWORD1
+sr_cmd_t	KEYWORD1
+sr_event_t	KEYWORD1
+sr_mode_t	KEYWORD1
+sr_channels_t	KEYWORD1
+sr_cb	KEYWORD1
+
+#######################################
+# Methods and Functions (KEYWORD2)
+#######################################
+
+onEvent	KEYWORD2
+setMode	KEYWORD2
+pause	KEYWORD2
+resume	KEYWORD2
+
+#######################################
+# Constants (LITERAL1)
+#######################################
+
+SR_EVENT_WAKEWORD	LITERAL1
+SR_EVENT_WAKEWORD_CHANNEL	LITERAL1
+SR_EVENT_COMMAND	LITERAL1
+SR_EVENT_TIMEOUT	LITERAL1
+SR_MODE_OFF	LITERAL1
+SR_MODE_WAKEWORD	LITERAL1
+SR_MODE_COMMAND	LITERAL1
+SR_MODE_MAX	LITERAL1
+SR_CHANNELS_MONO	LITERAL1
+SR_CHANNELS_STEREO	LITERAL1
+SR_CHANNELS_MAX	LITERAL1

libraries/ESP_SR/library.properties

@@ -0,0 +1,9 @@
+name=ESP_SR
+version=1.0.0
+author=me-no-dev
+maintainer=me-no-dev
+sentence=Library for ESP Sound Recognition
+paragraph=Supports ESP32 Arduino platforms.
+category=Sound
+url=https://github.com/espressif/arduino-esp32/
+architectures=esp32